courses:wshop:topics:tematy2024zima

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision		 Previous revision
courses:wshop:topics:tematy2024zima [2024/10/10 23:05] – kktcourses:wshop:topics:tematy2024zima [2025/02/18 11:48] (current) – [[KKT] Semantic Search 101] kkt
Line 17: Line 17:
 ==== [SBK] Counterfactual evaluation framework [other team: factual] ====  ==== [SBK] Counterfactual evaluation framework [other team: factual] ==== 
  
-  * **Student:** FIXME  {{:courses:xai:winner.png?30|}}+  * **Student:** Paulina Wojnarska  {{:courses:xai:winner.png?30|}}
   * **Namespace in the wiki:** [[..:projects:2024:cfeval:]]    * **Namespace in the wiki:** [[..:projects:2024:cfeval:]] 
   * **The goal of the project:** The goal of this project is to implement a Python module that will cover all of the evalaution metrics from: [[https://link.springer.com/article/10.1007/s10618-022-00831-6|Counterfactual explanations and how to find them: literature review and benchmarking]]. One of the most important aspect of the framework should be easy way to add your own method a server script making it possible to run evaluations and publish the results online automatically.   * **The goal of the project:** The goal of this project is to implement a Python module that will cover all of the evalaution metrics from: [[https://link.springer.com/article/10.1007/s10618-022-00831-6|Counterfactual explanations and how to find them: literature review and benchmarking]]. One of the most important aspect of the framework should be easy way to add your own method a server script making it possible to run evaluations and publish the results online automatically.
Line 25: Line 25:
   * **Links:**    * **Links:** 
     * [[https://link.springer.com/article/10.1007/s10618-022-00831-6|Counterfactual explanations and how to find them: literature review and benchmarking]]      * [[https://link.springer.com/article/10.1007/s10618-022-00831-6|Counterfactual explanations and how to find them: literature review and benchmarking]] 
-    * +    * https://christophm.github.io/interpretable-ml-book/
  
  ==== [SBK] Eyetracking for (Explainable) AI ====  ==== [SBK] Eyetracking for (Explainable) AI ====
  
   * **Student:** Sebastian Sęczyk,Jakub Pleśniak  {{:courses:xai:winner.png?30|}}   * **Student:** Sebastian Sęczyk,Jakub Pleśniak  {{:courses:xai:winner.png?30|}}
-  * **Namespace in the wiki:** [[..:projects:2024:tobiixai:start|Sebastian Sęczyk]], [[..:projects:2024:tobiixai2:start|Jakub Pleśniak]]+  * **Namespace in the wiki:** [[..:projects:2024:tobiixai:start|Sebastian Sęczyk]], [[..:projects:2024:tobiixai:start|Jakub Pleśniak]]
   * **The goal of the project:** Tool for data labeling supported with eyetracking   * **The goal of the project:** Tool for data labeling supported with eyetracking
   * **Technology:** python,tobii   * **Technology:** python,tobii
Line 48: Line 48:
  
 ==== [SBK] Explainable Hyperparameter optimization ==== ==== [SBK] Explainable Hyperparameter optimization ====
-  * **Student:** FIXME {{:courses:wshop:topics:peer.png?40|}} {{:courses:wshop:topics:fast.png?30|}} +  * **Student:** Agnieszka Felis, Mikołaj Golowski {{:courses:wshop:topics:peer.png?40|}} {{:courses:wshop:topics:fast.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:ixautoml:start]]
   * **The goal of the project:** Evaluation of several selected methods for explaianbel hyperparameter optimization   * **The goal of the project:** Evaluation of several selected methods for explaianbel hyperparameter optimization
   * **Technology:** Python, Keras/PyTorch, SHAP   * **Technology:** Python, Keras/PyTorch, SHAP
Line 69: Line 69:
  
 ==== [SBK] Dimensionality reduciton to speedup LUX ==== ==== [SBK] Dimensionality reduciton to speedup LUX ====
-  * **Student:** FIXME {{:courses:wshop:topics:fast.png?30|}} +  * **Student:** Jan Zoń {{:courses:wshop:topics:fast.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2043:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2043:luxspeedup:start]]
   * **The goal of the project:** The goal is to improve LUX software to perform calculation in reduced dimensionality space   * **The goal of the project:** The goal is to improve LUX software to perform calculation in reduced dimensionality space
   * **Technology:** Python, Keras/PyTorch   * **Technology:** Python, Keras/PyTorch
Line 79: Line 79:
  
 ==== [SBK] Neurosymbolic Neural Networks==== ==== [SBK] Neurosymbolic Neural Networks====
-  * **Student:** FIXME  {{:courses:xai:winner.png?30|}} +  * **Student:** Jakub Samel, Aliaxandr Zybaila  {{:courses:xai:winner.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:nsnn:start|Jakub Samel]], [[..:projects:2024:nsnn2:start|Aliaxandr Zybaila]]
   * **The goal of the project:** MVP is to implement the same exmaple (e.g. Sudoku Solver) in all of the linked methods.   * **The goal of the project:** MVP is to implement the same exmaple (e.g. Sudoku Solver) in all of the linked methods.
   * **Technology:** Python, Keras/PyTorch   * **Technology:** Python, Keras/PyTorch
Line 91: Line 91:
  
 ==== [SBK] Explainable AI for images==== ==== [SBK] Explainable AI for images====
-  * **Student:** FIXME  {{:courses:xai:winner.png?30|}} {{:courses:wshop:topics:peer.png?40|}} +  * **Student:** Jakub Siwy,  Jarek Such {{:courses:xai:winner.png?30|}} {{:courses:wshop:topics:peer.png?40|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:imgxai:start]]
   * **The goal of the project:** Implement and compare selected approaches for concept-based explanation of image classifiers   * **The goal of the project:** Implement and compare selected approaches for concept-based explanation of image classifiers
   * **Technology:** Python, Keras/PyTorch   * **Technology:** Python, Keras/PyTorch
Line 102: Line 102:
  
 ==== [SBK] Causal Autoencoder for anomaly detection==== ==== [SBK] Causal Autoencoder for anomaly detection====
-  * **Student:** FIXME  {{:courses:xai:winner.png?30|}} {{:courses:wshop:topics:peer.png?40|}} +  * **Student:** Natalia Kramarz  {{:courses:xai:winner.png?30|}} {{:courses:wshop:topics:peer.png?40|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:causalae:start]]
   * **The goal of the project:** Implement and compare anomaly detection algorithm with/without causality component   * **The goal of the project:** Implement and compare anomaly detection algorithm with/without causality component
   * **Technology:** Python, Keras/PyTorch   * **Technology:** Python, Keras/PyTorch
Line 117: Line 117:
   * **The goal of the project:** Development of a prototype demonstrating the use of knowledge graphs to provide high-level explanations   * **The goal of the project:** Development of a prototype demonstrating the use of knowledge graphs to provide high-level explanations
   * **Technology:** Python, Machine learning, XAI, Semantic web   * **Technology:** Python, Machine learning, XAI, Semantic web
-  * **Description:** Currently existing explainable AI methods that aim to explain the performance of black-box machine learning models focus on feature importance. That is, the output from XAI methods is information about which features contribute most to a decision. But in situations where the model has a large number of parameters, such an explanation may be incomprehensible even to data analysts (as it certainly will be to system users). A much better situation would be to have an ontology/knowledge graph describing the relationships between features, which would allow translating the output from XAI methods into something more high-level (at the level of concepts/classes instead of individual features). Preparing a prototype that implements this task is the goal of this project. The project will involve (a) creation of basic ML model with XAI layer, (b) development of an ontology, <nowiki>(c)</nowiki> development of methods for translating low-level explanations into high-level ones (the last point will be the core issue of the project).+  * **Description:** Currently existing explainable AI methods that aim to explain the performance of black-box machine learning models focus on feature importance. That is, the output from XAI methods is information about which features contribute most to a decision. But in situations where the model has a large number of parameters, such an explanation may be incomprehensible even to data analysts (as it certainly will be to system users). A much better situation would be to have an ontology/knowledge graph describing the relationships between features, which would allow translating the output from XAI methods into something more high-level (at the level of concepts/classes instead of individual features). Preparing a prototype that implements this task is the goal of this project. The project will involve (a) creation of basic ML model with XAI layer (with SHAP?), (b) development of an ontology, <nowiki>(c)</nowiki> development of methods for translating low-level explanations into high-level ones (the last point will be the core issue of the project).
   * **Links:**   * **Links:**
     * Starting point: [[https://doi.org/10.1016/j.artint.2021.103627|Knowledge graphs as tools for explainable machine learning: A survey]]     * Starting point: [[https://doi.org/10.1016/j.artint.2021.103627|Knowledge graphs as tools for explainable machine learning: A survey]]
Line 123: Line 123:
 ==== [KKT] JU cultural heritage in Linked Open Data ==== ==== [KKT] JU cultural heritage in Linked Open Data ====
  
-  * **Student:** FIXME {{:courses:xai:winner.png?30|}}+  * **Student:** Lena Kaczanowska {{:courses:xai:winner.png?30|}}
   * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]   * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]
   * **The goal of the project:** Preparation of a knowledge graph that is a subset of the Linked Open Data cloud describing the cultural heritage of our university   * **The goal of the project:** Preparation of a knowledge graph that is a subset of the Linked Open Data cloud describing the cultural heritage of our university
Line 134: Line 134:
  
   * **Student:** Aleksandra Jaroszek, Maciej Struski {{:courses:xai:winner.png?30|}}   * **Student:** Aleksandra Jaroszek, Maciej Struski {{:courses:xai:winner.png?30|}}
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:sociallife:]]
   * **The goal of the project:** Preparation of workflow for automatic social life documents summarization (in form of tags and titles)   * **The goal of the project:** Preparation of workflow for automatic social life documents summarization (in form of tags and titles)
   * **Technology:** Python, machine learning, data analysis, LLM   * **Technology:** Python, machine learning, data analysis, LLM
Line 147: Line 147:
 ==== [KKT] Semantic Search 101 ==== ==== [KKT] Semantic Search 101 ====
  
-  * **Student:** FIXME {{:courses:wshop:topics:fast.png?30|}} +  * **Student:** Dominika Głowacka, Mikołaj Szymański {{:courses:wshop:topics:fast.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:semsearch:]]
   * **The goal of the project:** Preparation of a working semantic search demo for cultural heritage knowledge   * **The goal of the project:** Preparation of a working semantic search demo for cultural heritage knowledge
   * **Technology:** Python, Semantic Web, natural language processing   * **Technology:** Python, Semantic Web, natural language processing
Line 167: Line 167:
 ==== [KKT] GraphRAG 101 ==== ==== [KKT] GraphRAG 101 ====
  
-  * **Student:** FIXME {{:courses:wshop:topics:fast.png?30|}} +  * **Student:** Ewa Kobrzyńska, Emilia Górnisiewicz {{:courses:wshop:topics:fast.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:graphrag1:|Ewa Kobrzyńska]], [[..:projects:2024:graphrag2:|Emilia Górnisiewicz]]
   * **The goal of the project:** Preparation of a working GraphRAG demo for cultural heritage domain   * **The goal of the project:** Preparation of a working GraphRAG demo for cultural heritage domain
   * **Technology:** Python/Java, Semantic Web, LLM   * **Technology:** Python/Java, Semantic Web, LLM
Line 179: Line 179:
 ==== [KKT] FACE APIs comparison (cont.) ==== ==== [KKT] FACE APIs comparison (cont.) ====
  
-  * **Student:** FIXME {{:courses:xai:winner.png?30|}} +  * **Student:** Magdalena Gancarek, Klaudia Korczak {{:courses:xai:winner.png?30|}} 
-  * **Namespace in the wiki:** [[..:projects:2024:FIXME:]]+  * **Namespace in the wiki:** [[..:projects:2024:faceapis:]]
   * **The goal of the project:** Comparison of the effectiveness of off-the-shelf APIs and pre-trained models for emotion recognition in non-trivial images   * **The goal of the project:** Comparison of the effectiveness of off-the-shelf APIs and pre-trained models for emotion recognition in non-trivial images
   * **Technology:** Python, data analysis   * **Technology:** Python, data analysis
  • courses/wshop/topics/tematy2024zima.1728601503.txt.gz
  • Last modified: 6 months ago
  • by kkt