--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:4030 - loss:MultipleNegativesRankingLoss base_model: sentence-transformers/all-distilroberta-v1 widget: - source_sentence: What is the contact email for Dr. Amr Ashraf Mohamed Amin? sentences: - "Topic: Second Level Courses (Mainstream)\nSummary: Outlines the course list for\ \ the third and fourth semesters, including course codes, titles, credit hours,\ \ and prerequisites.\nChunk: \"Second Level Courses (Mainstream) \nThird Semester\n\ \ • HUM113: Report Writing (2 Credit Hours) \n• CIS250: Object-Oriented Programming\ \ (3 Credit Hours) – Prerequisite: CIS150 \n(Structured Programming) \n• BSC221:\ \ Discrete Mathematics (3 Credit Hours) \n• CIS260: Logic Design (3 Credit Hours)\ \ – Prerequisite: BSC121 (Physics I) \n• CIS280: Database Management Systems (3\ \ Credit Hours) – Prerequisite: CIS150 \n(Structured Programming) \n• CIS240:\ \ Statistical Analysis (3 Credit Hours) – Prerequisite: BSC123 (Probability &\ \ \nStatistics) \n• Total Credit Hours: 17 \nFourth Semester \n• CIS220: Computer\ \ Organization & Architecture (3 Credit Hours) – Prerequisite: CIS260 \n(Logic\ \ Design) \n• CIS270: Data Structure (3 Credit Hours) – Prerequisite: CIS250 (Object-Oriented\ \ \nProgramming) \n• BSC225: Linear Algebra (3 Credit Hours) \n• CIS230: Operations\ \ Research (3 Credit Hours) \n• CIS243: Artificial Intelligence (3 Credit Hours)\ \ – Prerequisite: CIS150 (Structured \nProgramming) \n• Total Credit Hours: 15\"" - 'The final exam for the Structured programming course, offered by the general department, from 2022, is available at the following link: [https://drive.google.com/file/d/1Bpqoa78DcFNC8335i7vucV0nBN-J01v9/view?usp=sharing' - Dr. Amr Ashraf Mohamed Amin is part of the Unknown department and can be reached at amr.amin.stdsw@cis.asu.edu.eg. - source_sentence: What systems have been developed for quickly locating missing children? sentences: - 'The final exam for Digital Signal Processing course, offered by the computer science department, from 2024, is available at the following link: [https://drive.google.com/file/d/1RO0aPoom-TA-qgsopwR9krszD_pQIzfJ/view?usp=sharing' - '**Lost People Finder** ### **Abstract** **Missing Persons Statistics** Recently, there has been a clear increase in the population. As stated in a 2005 report, published by the US Department of Justice, over 340,500 of children''s population go missing, from their parents, for at least an hour. Not only was this issue minor in between children, but also it has been evident that the elderly and people with special needs seem missing whenever their guardians get distracted. **Lost People Finder Application** Through the Lost People Finder application, we can search for missing people quickly and efficiently by entering the missing person''s picture in the application, and the application searches for him immediately.' - 'The final exam for the English 1course, offered by the general department, from 2022, is available at the following link: [https://drive.google.com/file/d/1IbqLbHuyZoDyhsL1BERpI2P0iLFZmgt8/view].' - source_sentence: What are the conditions for the College Council granting a final chance? sentences: - Dr. Zeina Rayan is part of the Unknown department and can be reached at zeinarayan@cis.asu.edu.eg. - 'Topic: Academic Warning and Dismissal Summary: Students receive academic warnings for low GPAs and may be dismissed if the GPA remains low for six semesters or if graduation requirements aren''t met within double the study years. Students can re-study courses to improve their average, with certain conditions and grade limits. Chunk: "Academic warning - dismissal from study - mechanisms of raising the cumulative average 1. The student is given an academic warning if he obtains a cumulative average less than "2" for any semester that he must raise his cumulative average to at least 2.00. 2. A student who is academically probated is dismissed from the study if the GPA drops below 2.00 is repeated during six main semesters. 3. If the student does not meet the graduation requirements within the maximum period of study, which is double the years of study according to the law, he will be dismissed. 4. The College Council may consider the possibility of granting the student exposed to dismissal as a result of his inability to raise his cumulative average to At least one and final chance of two semesters to raise his/her GPA to 2.00 and meet graduation requirements if he/she has successfully completed at least 80% of the credit hours required for graduation. 5. The student may re-study the courses in which he has previously passed in order to improve the cumulative average, and the repetition is a study and an exam, and the grade he obtained the last time he studied the course is calculated for him. A maximum of (5) courses unless the improvement is for the purpose of raising the academic warning or achieving the graduation requirements, and in all cases, both grades are mentioned in his academic record. 6. For the student to re-study a course in which he has previously obtained a grade of (F), the grade he obtained in the repetition is calculated with a maximum of (B), and for calculating the cumulative average, the last grade is calculated for him only, provided that both grades are mentioned in the student''s academic record."' - '**Abstract** **Introduction to Renewable Energy** Renewable energy is gaining great importance nowadays. Solar energy is one of the most popular renewable energy sources as it is carbon dioxide free, has low operating costs, and its exploitation helps improve public health. **Project Overview** This project deals with the introduction of an embedded automatic solar energy tracking system that can be monitored remotely. The main objective of the system is to exploit the maximum amount of sunlight and convert it into electricity so that it can be used easily and efficiently. This can be done by rendering and aligning a model that drives the solar panels to be perpendicular to and track the sun''s rays so that more energy is generated. **Advantages of the Tracker System** The main advantage of this tracker is that the various readings received from the sensors can be tracked remotely with a decentralized technological system that allows analysis of results, detection of faults and making tracking decisions. The advantage of this system is to provide access to a permanent and contamination-free power supply source. When connected to large battery banks, they can independently fill the needs of local areas.' - source_sentence: How can I contact Dr. Doaa Mahmoud? sentences: - Dr. Hanan Hindy is part of the CS department and can be reached at hanan.hindy@cis.asu.edu.eg. - 'The final exam for Database Management System course, offered by the general department, from 2019, is available at the following link: [https://drive.google.com/file/d/1OOIPr48WI8Cm3TVzPdel2Dh3SZUQTVxA/view' - Dr. Doaa Mahmoud is part of the Unknown department and can be reached at Doaa.Mahmoud@cis.asu.edu.eg. - source_sentence: Where can I find Abdel Badi Salem's email address? sentences: - '# **Abstract** ## **Introduction** One of the main issues we are aiming to help in society are those of the disabled. Disabilities do not have a single type or manner in which it attacks the body but comes in a very wide range. At the present time, the amount of disabled people is **increasing annually**, so we aim to make a standard wheelchair to aid the mobility of disabled people who cannot walk; by designing two mechanisms, one uses eye-movement guidance and the other uses EEG Signals, which goes through pre-processing stage to extract more information from the data. This'' done by segmentation using a window of size 200 (Sampling frequency), then features extraction. That takes us to classification, the highest accuracy we got is on subject [E] for motor imaginary dataset on Classical paradigm, Multi Level Perceptron classifier (with accuracy of 60.5%), The result of this classification''s used as a command to move the wheelchair after that.' - '# **Abstract** ## **Sports Analytics Overview** Sports analytics has been successfully applied in sports like football and basketball. However, its application in soccer has been limited. Research in soccer analytics with Machine Learning techniques is limited and is mostly employed only for predictions. There is a need to find out if the application of Machine Learning can bring better and more insightful results in soccer analytics. In this thesis, we perform descriptive as well as predictive analysis of soccer matches and player performances. ## **Football Rating Analysis** In football, it is popular to rely on ratings by experts to assess a player''s performance. However, the experts do not unravel the criteria they use for their rating. We attempt to identify the most important attributes of player''s performance which determine the expert ratings. In this way we find the latent knowledge which the experts use to assign ratings to players. We performed a series of classifications with three different pruning strategies and an array of Machine Learning algorithms. The best results for predicting ratings using performance metrics had mean absolute error of 0.17. We obtained a list of most important performance metrics for each of the playing positions which approximates the attributes considered by the experts for assigning ratings. Then we find the most influential performance metrics of the players for determining the match outcome and we examine the extent to which the outcome is characterized by the performance attributes of the players. We found 34 performance attributes' - Dr. Abdel Badi Salem is part of the CS department and can be reached at absalem@cis.asu.edu.eg. pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on sentence-transformers/all-distilroberta-v1 results: - task: type: information-retrieval name: Information Retrieval dataset: name: ai college validation type: ai-college-validation metrics: - type: cosine_accuracy@1 value: 0.18810557968593383 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.4186435015035082 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5676578683595055 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8463080521216171 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.18810557968593383 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.13954783383450275 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1135315736719011 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08463080521216171 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.18810557968593383 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.4186435015035082 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5676578683595055 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8463080521216171 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47259073953229414 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3588172667440963 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3678298256041653 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.18843969261610424 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.4173070497828266 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5669896424991647 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8456398262612763 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.18843969261610424 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.13910234992760886 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11339792849983296 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08456398262612765 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.18843969261610424 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.4173070497828266 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5669896424991647 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8456398262612763 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47223133269915585 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3585802056650706 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3676667485080777 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.1102813476901702 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.3218131295588746 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5451545675581799 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8817297672803056 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.1102813476901702 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.1072710431862915 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.10903091351163598 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08817297672803058 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.1102813476901702 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.3218131295588746 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5451545675581799 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8817297672803056 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4323392922230707 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.2959338835684789 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.30305652186931414 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.18576678917474107 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.42064817908453056 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5699966588706983 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.858002004677581 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.18576678917474107 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.14021605969484352 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11399933177413965 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08580020046775809 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.18576678917474107 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.42064817908453056 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5699966588706983 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.858002004677581 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47488287423350733 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.35840307277828215 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3669503238927413 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.1827597728032075 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.42198463080521215 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5750083528232542 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8683595055128633 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.1827597728032075 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.14066154360173738 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11500167056465085 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08683595055128634 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.1827597728032075 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.42198463080521215 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5750083528232542 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8683595055128633 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4780584736286147 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3594039531393358 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3674823360981191 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.17674574006014032 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.42098229201470094 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5720013364517207 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8763782158369529 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.17674574006014032 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.140327430671567 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11440026729034415 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08763782158369529 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.17674574006014032 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.42098229201470094 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5720013364517207 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8763782158369529 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47784861917490756 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.356773211567732 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3644323168133691 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.17674574006014032 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.42098229201470094 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5720013364517207 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8763782158369529 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.17674574006014032 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.140327430671567 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11440026729034415 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08763782158369529 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.17674574006014032 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.42098229201470094 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5720013364517207 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8763782158369529 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47784861917490756 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.356773211567732 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3644323168133691 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: ai college modefied validation type: ai-college_modefied-validation metrics: - type: cosine_accuracy@1 value: 0.1127127474817645 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.3218131295588746 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5481069815908302 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8931920805835359 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.1127127474817645 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.10727104318629153 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.10962139631816603 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08931920805835358 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.1127127474817645 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.3218131295588746 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5481069815908302 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8931920805835359 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4379716529188091 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.2999361137299657 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.30656764876713344 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.10993400486279958 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.32737061479680446 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5489753386592567 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8989232372351511 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.10993400486279958 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.10912353826560146 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.10979506773185134 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08989232372351512 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.10993400486279958 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.32737061479680446 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5489753386592567 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8989232372351511 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.43927652334969547 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.2998494158575775 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.30624915588054374 name: Cosine Map@100 - type: cosine_accuracy@1 value: 0.10993400486279958 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.3268496005557485 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.548627995831886 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8989232372351511 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.10993400486279958 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.10894986685191616 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.10972559916637721 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08989232372351512 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.10993400486279958 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.3268496005557485 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.548627995831886 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8989232372351511 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.43919844728741414 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.29975865186875866 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3061583918917249 name: Cosine Map@100 --- # SentenceTransformer based on sentence-transformers/all-distilroberta-v1 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("Bo8dady/finetuned3-College-embeddings") # Run inference sentences = [ "Where can I find Abdel Badi Salem's email address?", 'Dr. Abdel Badi Salem is part of the CS department and can be reached at absalem@cis.asu.edu.eg.', "# **Abstract**\n\n## **Sports Analytics Overview**\nSports analytics has been successfully applied in sports like football and basketball. However, its application in soccer has been limited. Research in soccer analytics with Machine Learning techniques is limited and is mostly employed only for predictions. There is a need to find out if the application of Machine Learning can bring better and more insightful results in soccer analytics. In this thesis, we perform descriptive as well as predictive analysis of soccer matches and player performances.\n\n## **Football Rating Analysis**\nIn football, it is popular to rely on ratings by experts to assess a player's performance. However, the experts do not unravel the criteria they use for their rating. We attempt to identify the most important attributes of player's performance which determine the expert ratings. In this way we find the latent knowledge which the experts use to assign ratings to players. We performed a series of classifications with three different pruning strategies and an array of Machine Learning algorithms. The best results for predicting ratings using performance metrics had mean absolute error of 0.17. We obtained a list of most important performance metrics for each of the playing positions which approximates the attributes considered by the experts for assigning ratings. Then we find the most influential performance metrics of the players for determining the match outcome and we examine the extent to which the outcome is characterized by the performance attributes of the players. We found 34 performance attributes", ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Information Retrieval * Datasets: `ai-college-validation`, `ai-college_modefied-validation`, `ai-college-validation`, `ai-college_modefied-validation`, `ai-college-validation`, `ai-college_modefied-validation` and `ai-college-validation` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | ai-college-validation | ai-college_modefied-validation | |:--------------------|:----------------------|:-------------------------------| | cosine_accuracy@1 | 0.1767 | 0.1099 | | cosine_accuracy@3 | 0.421 | 0.3268 | | cosine_accuracy@5 | 0.572 | 0.5486 | | cosine_accuracy@10 | 0.8764 | 0.8989 | | cosine_precision@1 | 0.1767 | 0.1099 | | cosine_precision@3 | 0.1403 | 0.1089 | | cosine_precision@5 | 0.1144 | 0.1097 | | cosine_precision@10 | 0.0876 | 0.0899 | | cosine_recall@1 | 0.1767 | 0.1099 | | cosine_recall@3 | 0.421 | 0.3268 | | cosine_recall@5 | 0.572 | 0.5486 | | cosine_recall@10 | 0.8764 | 0.8989 | | **cosine_ndcg@10** | **0.4778** | **0.4392** | | cosine_mrr@10 | 0.3568 | 0.2998 | | cosine_map@100 | 0.3644 | 0.3062 | #### Information Retrieval * Dataset: `ai-college-validation` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1884 | | cosine_accuracy@3 | 0.4173 | | cosine_accuracy@5 | 0.567 | | cosine_accuracy@10 | 0.8456 | | cosine_precision@1 | 0.1884 | | cosine_precision@3 | 0.1391 | | cosine_precision@5 | 0.1134 | | cosine_precision@10 | 0.0846 | | cosine_recall@1 | 0.1884 | | cosine_recall@3 | 0.4173 | | cosine_recall@5 | 0.567 | | cosine_recall@10 | 0.8456 | | **cosine_ndcg@10** | **0.4722** | | cosine_mrr@10 | 0.3586 | | cosine_map@100 | 0.3677 | #### Information Retrieval * Dataset: `ai-college-validation` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1103 | | cosine_accuracy@3 | 0.3218 | | cosine_accuracy@5 | 0.5452 | | cosine_accuracy@10 | 0.8817 | | cosine_precision@1 | 0.1103 | | cosine_precision@3 | 0.1073 | | cosine_precision@5 | 0.109 | | cosine_precision@10 | 0.0882 | | cosine_recall@1 | 0.1103 | | cosine_recall@3 | 0.3218 | | cosine_recall@5 | 0.5452 | | cosine_recall@10 | 0.8817 | | **cosine_ndcg@10** | **0.4323** | | cosine_mrr@10 | 0.2959 | | cosine_map@100 | 0.3031 | #### Information Retrieval * Dataset: `ai-college-validation` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1858 | | cosine_accuracy@3 | 0.4206 | | cosine_accuracy@5 | 0.57 | | cosine_accuracy@10 | 0.858 | | cosine_precision@1 | 0.1858 | | cosine_precision@3 | 0.1402 | | cosine_precision@5 | 0.114 | | cosine_precision@10 | 0.0858 | | cosine_recall@1 | 0.1858 | | cosine_recall@3 | 0.4206 | | cosine_recall@5 | 0.57 | | cosine_recall@10 | 0.858 | | **cosine_ndcg@10** | **0.4749** | | cosine_mrr@10 | 0.3584 | | cosine_map@100 | 0.367 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 4,030 training samples * Columns: Question and chunk * Approximate statistics based on the first 1000 samples: | | Question | chunk | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | Question | chunk | |:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Could you share the link to the 2018 Distributed Computing final exam? | The final exam for Distributed Computing course, offered by the computer science department, from 2018, is available at the following link: [https://drive.google.com/file/d/1YSzMeYStlFEztP0TloIcBqnfPr60o4ez/view?usp=sharing | | What databases exist for footstep recognition research? | **Abstract**

**Documentation Overview**
This documentation reports an experimental analysis of footsteps as a biometric. The focus here is on information extracted from the time domain of signals collected from an array of piezoelectric sensors.

**Database Information**
Results are related to the largest footstep database collected to date, with almost 20,000 valid footstep signals and more than 120 persons, which is well beyond previous related databases.

**Feature Extraction**
Three feature approaches have been extracted, the popular ground reaction force (GRF), the spatial average and the upper and lower contours of the pressure signals.

**Experimental Results**
Experimental work is based on a verification mode with a holistic approach based on PCA and SVM, achieving results in the range of 5 to 15% equal error rate(EER) depending on the experimental conditions of quantity of data used in the reference models. | | Is there a maximum duration of study specified in the text? | Topic: Duration of Study
Summary: A bachelor's degree at the Faculty of Computers and Information requires at least four years of study, contingent on fulfilling degree requirements.
Chunk: "Duration of study
• The duration of study at the Faculty of Computers and Information to obtain a bachelor's degree is not less than 4 years, provided that the requirements for obtaining the scientific degree are completed." | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 575 evaluation samples * Columns: Question and chunk * Approximate statistics based on the first 575 samples: | | Question | chunk | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | Question | chunk | |:---------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Are there projects that use machine learning for automatic brain tumor identification? | # **Abstract**

## **Brain and Tumor Description**
A human brain is center of the nervous system; it is a collection of white mass of cells. A tumor of brain is collection of uncontrolled increasing of these cells abnormally found in different part of the brain namely Glial cells, neurons, lymphatic tissues, blood vessels, pituitary glands and other part of brain which lead to the cancer.

## **Detection and Identification**
Manually it is not so easily possible to detect and identify the tumor. Programming division method by MRI is way to detect and identify the tumor. In order to give precise output a strong segmentation method is needed. Brain tumor identification is really challenging task in early stages of life. But now it became advanced with various machine learning and deep learning algorithms. Now a day's issue of brain tumor automatic identification is of great interest. In Order to detect the brain tumor of a patient we consider the data of patients like MRI images of a pat... | | Are there studies that propose solutions to the challenges of plant pest detection using deep learning? | **Abstract**

**Introduction**
Identification of the plant diseases is the key to preventing the losses in the yield and quantity of the agricultural product. Disease diagnosis based on the detection of early symptoms is a usual threshold taken into account for integrated pest management strategies. through deep learning methodologies, plant diseases can be detected and diagnosed.

**Study Discussion**
On this basis, this study discusses possible challenges in practical applications of plant diseases and pests detection based on deep learning. In addition, possible solutions and research ideas are proposed for the challenges, and several suggestions are given. Finally, this study gives the analysis and prospect of the future trend of plant diseases and pests detection based on deep learning.

5 | Page | | Is there a link available for the 2025 Calc 1 course exam? | The final exam for the calculus1 course, offered by the general department, from 2025, is available at the following link: [https://drive.google.com/file/d/1g8iiGUo4HCUzNNWBJJrW1QZAsz-RYehw/view?usp=sharing]. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 1e-06 - `num_train_epochs`: 10 - `warmup_ratio`: 0.2 - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 1e-06 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 10 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.2 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `tp_size`: 0 - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | ai-college-validation_cosine_ndcg@10 | ai-college_modefied-validation_cosine_ndcg@10 | |:------:|:----:|:-------------:|:---------------:|:------------------------------------:|:---------------------------------------------:| | -1 | -1 | - | - | 0.4208 | - | | 0.3968 | 100 | 0.1371 | 0.0785 | 0.4483 | - | | 0.7937 | 200 | 0.0575 | 0.0357 | 0.4600 | - | | 1.1905 | 300 | 0.0346 | 0.0286 | 0.4640 | - | | 1.5873 | 400 | 0.0313 | 0.0264 | 0.4698 | - | | 1.9841 | 500 | 0.0189 | 0.0256 | 0.4716 | - | | 2.3810 | 600 | 0.021 | 0.0249 | 0.4703 | - | | 2.7778 | 700 | 0.0264 | 0.0247 | 0.4726 | - | | -1 | -1 | - | - | 0.4252 | - | | 0.3968 | 100 | 0.0132 | 0.0238 | 0.4277 | - | | 0.7937 | 200 | 0.0192 | 0.0221 | 0.4295 | - | | 1.1905 | 300 | 0.0169 | 0.0214 | 0.4316 | - | | 1.5873 | 400 | 0.02 | 0.0200 | 0.4315 | - | | 1.9841 | 500 | 0.0124 | 0.0201 | 0.4315 | - | | 2.3810 | 600 | 0.0152 | 0.0195 | 0.4311 | - | | 2.7778 | 700 | 0.0189 | 0.0193 | 0.4309 | - | | 3.1746 | 800 | 0.0222 | 0.0182 | 0.4307 | - | | 3.5714 | 900 | 0.0158 | 0.0182 | 0.4312 | - | | 3.9683 | 1000 | 0.0144 | 0.0181 | 0.4311 | - | | 4.3651 | 1100 | 0.0237 | 0.0176 | 0.4315 | - | | 4.7619 | 1200 | 0.0132 | 0.0178 | 0.4323 | - | | -1 | -1 | - | - | 0.4749 | 0.4326 | | 0.3968 | 100 | 0.0077 | 0.0175 | - | 0.4322 | | 0.7937 | 200 | 0.0116 | 0.0171 | - | 0.4320 | | 1.1905 | 300 | 0.0093 | 0.0169 | - | 0.4339 | | 1.5873 | 400 | 0.0125 | 0.0160 | - | 0.4340 | | 1.9841 | 500 | 0.0083 | 0.0161 | - | 0.4340 | | 2.3810 | 600 | 0.0105 | 0.0156 | - | 0.4350 | | 2.7778 | 700 | 0.0132 | 0.0155 | - | 0.4357 | | 3.1746 | 800 | 0.0161 | 0.0145 | - | 0.4362 | | 3.5714 | 900 | 0.0113 | 0.0144 | - | 0.4372 | | 3.9683 | 1000 | 0.0112 | 0.0140 | - | 0.4368 | | 4.3651 | 1100 | 0.0185 | 0.0136 | - | 0.4366 | | 4.7619 | 1200 | 0.0101 | 0.0139 | - | 0.4367 | | 5.1587 | 1300 | 0.0118 | 0.0138 | - | 0.4366 | | 5.5556 | 1400 | 0.0145 | 0.0139 | - | 0.4366 | | 5.9524 | 1500 | 0.0104 | 0.0139 | - | 0.4376 | | 6.3492 | 1600 | 0.0105 | 0.0137 | - | 0.4380 | | 6.7460 | 1700 | 0.0125 | 0.0137 | - | 0.4380 | | -1 | -1 | - | - | 0.4781 | 0.4375 | | 0.3968 | 100 | 0.0054 | 0.0135 | - | 0.4380 | | 0.7937 | 200 | 0.0078 | 0.0133 | - | 0.4374 | | 1.1905 | 300 | 0.0053 | 0.0132 | - | 0.4381 | | 1.5873 | 400 | 0.0077 | 0.0127 | - | 0.4387 | | 1.9841 | 500 | 0.0054 | 0.0129 | - | 0.4374 | | 2.3810 | 600 | 0.0067 | 0.0122 | - | 0.4392 | | 2.7778 | 700 | 0.0094 | 0.0120 | - | 0.4387 | | 3.1746 | 800 | 0.0111 | 0.0116 | - | 0.4360 | | 3.5714 | 900 | 0.0079 | 0.0113 | - | 0.4368 | | 3.9683 | 1000 | 0.0081 | 0.0111 | - | 0.4369 | | 4.3651 | 1100 | 0.0134 | 0.0109 | - | 0.4375 | | 4.7619 | 1200 | 0.0072 | 0.0110 | - | 0.4371 | | 5.1587 | 1300 | 0.0091 | 0.0109 | - | 0.4378 | | 5.5556 | 1400 | 0.0121 | 0.0111 | - | 0.4379 | | 5.9524 | 1500 | 0.0081 | 0.0111 | - | 0.4376 | | 6.3492 | 1600 | 0.008 | 0.0110 | - | 0.4376 | | 6.7460 | 1700 | 0.0103 | 0.0109 | - | 0.4389 | | 7.1429 | 1800 | 0.013 | 0.0108 | - | 0.4397 | | 7.5397 | 1900 | 0.0134 | 0.0109 | - | 0.4385 | | 7.9365 | 2000 | 0.0133 | 0.0108 | - | 0.4398 | | 8.3333 | 2100 | 0.0109 | 0.0109 | - | 0.4389 | | 8.7302 | 2200 | 0.0109 | 0.0107 | - | 0.4386 | | 9.1270 | 2300 | 0.0077 | 0.0104 | - | 0.4395 | | 9.5238 | 2400 | 0.0107 | 0.0104 | - | 0.4387 | | 9.9206 | 2500 | 0.0117 | 0.0104 | - | 0.4393 | | -1 | -1 | - | - | 0.4778 | 0.4392 | ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 3.4.1 - Transformers: 4.51.1 - PyTorch: 2.5.1+cu124 - Accelerate: 1.3.0 - Datasets: 3.5.0 - Tokenizers: 0.21.0 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```