Starts July 24th 2022

The summer course Explainable AI with Python is a joint collaboration between LAMBDA LAB, Tel Aviv University and W-AI. Registration is free for both women and men. 

Course Syllabus

Registration Form

 

 

Guest Talk Abstracts 
 

Dr Claudia Goldman, Staff Researcher, General Motors 24th July 

 

Title: Bridging the communication gap between humans and machines

 

Trust in automated machines, controlled by AI algorithms (e.g., decision making under uncertainty), is essential for their users’ acceptance and effective use of these systems. However, assessing these solutions, solely, by their prediction accuracy and the (mathematical) optimality might not provide the transparency needed by users to understand why these systems are behaving as they learned to do. We suggest adding eXplainability capabilities to these AI algorithms (XAI) to bridge this gap between humans’ expectations and advanced decision-making solutions. First, we present an algorithm to explain semantically why a prediction was classified, supported by results from learning the semantics of two classifiers, trained to predict AV driving comfort and driving trajectories. Then, we discuss current state of the art in explainable AI for planning systems, comparing it to the users’ needs discovered in data collected from interactions with simulated AV behaviors.

 

Shelly Shenin, AI Research Engineer, Meta  AI, 27th July 

  

KNN-Diffusion: Image Generation via Large-Scale Retrieval

 

Paper: https://arxiv.org/pdf/2204.02849.pdf

 

While the availability of massive Text-Image datasets is shown to be extremely useful in training large-scale gener- ative models (e.g. DDPMs, Transformers), their output typ- ically depends on the quality of both the input text, as well as the training dataset. In this work, we show how large- scale retrieval methods, in particular efficient K-Nearest- Neighbors (KNN) search, can be used in order to train a model to adapt to new samples. Learning to adapt enables several new capabilities. Sifting through billions of records at inference time is extremely efficient and can alleviate the need to train or memorize an adequately large genera- tive model. Additionally, fine-tuning trained models to new samples can be achieved by simply adding them to the ta- ble. Rare concepts, even without any presence in the train- ing set, can be then leveraged during test time without any modification to the generative model. Our diffusion-based model trains on images only, by leveraging a joint Text- Image multi-modal metric. Compared to baseline meth- ods, our generations achieve state of the art results both in human evaluations as well as with perceptual scores when tested on a public multimodal dataset of natural images, as well as on a collected dataset of 400 million Stickers. 

 

​
 

Adi Watzman, Research Scientist at PayPal, 31st July 

 

SHAP Values for ML Explainability

 

How do ML models use their features to make predictions?

SHAP opens up the ML black box by providing feature attributions for every prediction of every model. Since being published in 2017 (https://arxiv.org/abs/1705.07874), SHAP has gained popularity extremely quickly thanks to its user-friendly API and theoretical guarantees. In this talk I will guide your intuition through the exciting theory SHAP is based on, and demonstrate how SHAP values can be aggregated to understand model behavior. Throughout the talk I will present real-life examples for using SHAP in the fraud detection domain at PayPal.

 

 

 

Leigh Eitan, Data Scientist at Intel AI Group, 31st July 

 

Mind The Path: Path-based KnowledgeGraph with Neural Attention

 

Knowledge-graphs (KG) recommender systems utilize both Collaborative Filtering (CF) data together with an informative knowledge-graph on the items in order to improve prediction accuracy. Path-based KG methods explore the interlinks within a knowledge graph in order to enhance the connectivity between users and items with rich complementary information. A key advantage of path-based KG methods over embedding methods stems from their ability to naturally enable intuitive explanations. In this work, we present a novel path-based algorithm which employs neural attention in order to better extract the relevant information on the KG paths. Evaluations of public KG recommendation datasets indicate a clear advantage to the proposed method when compared to state-of-the-art path-based alternatives. Furthermore, we demonstrate the ability of our approach to generate clear and intuitive explanations which provide interpretability and improve user trust.

​

​

Michal Moshkovitz, Postdoc, TAU, 3rd Aug 

 

Explainable k-Means Clustering

 

Many clustering algorithms lead to cluster assignments that are hard to explain, partially because they complicatedly depend on data features. To improve interpretability, we consider using a small decision tree to define the clustering. We show that popular top-down decision tree algorithms may lead to clusterings with an arbitrarily high cost. On the positive side, we design a new algorithm that is O(k^2)-approximation compared to the optimal k-means. Prior to our work, no algorithms were known to have provable guarantees independent of dimension and input size. Empirically, we validate that the new algorithm produces a low-cost clustering, outperforming both standard decision tree methods and other algorithms for explainable clustering. Implementation available at https://github.com/navefr/ExKMC.

 

 

 

Vivian Levin, MSc, TAU, 10th Aug 

 

Gender Bias in AI Recruitment Systems based on  Machine Learning Analysis of LinkedIn Profiles.

 

In process of publication. 

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​