Learning to maximize mutual information for dynamic feature selection
Feature selection helps reduce data acquisition costs in ML, but the standard approach is to
train models with static feature subsets. Here, we consider the dynamic feature selection …
train models with static feature subsets. Here, we consider the dynamic feature selection …
Information maximization perspective of orthogonal matching pursuit with applications to explainable ai
A Chattopadhyay, R Pilgrim… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Information Pursuit (IP) is a classical active testing algorithm for predicting an output
by sequentially and greedily querying the input in order of information gain. However, IP is …
by sequentially and greedily querying the input in order of information gain. However, IP is …
Interpretability Guarantees with Merlin-Arthur Classifiers
We propose an interactive multi-agent classifier that provides provable interpretability
guarantees even for complex agents such as neural networks. These guarantees consist of …
guarantees even for complex agents such as neural networks. These guarantees consist of …
Variational information pursuit for interpretable predictions
There is a growing interest in the machine learning community in developing predictive
algorithms that are" interpretable by design". Towards this end, recent work proposes to …
algorithms that are" interpretable by design". Towards this end, recent work proposes to …
Bootstrapping variational information pursuit with large language and vision models for interpretable image classification
Variational Information Pursuit (V-IP) is an interpretable-by-design framework that makes
predictions by sequentially selecting a short chain of user-defined, interpretable queries …
predictions by sequentially selecting a short chain of user-defined, interpretable queries …
Knowledge Pursuit Prompting for Zero-Shot Multimodal Synthesis
Hallucinations and unfaithful synthesis due to inaccurate prompts with insufficient semantic
details are widely observed in multimodal generative models. A prevalent strategy to align …
details are widely observed in multimodal generative models. A prevalent strategy to align …
3VL: using Trees to teach Vision & Language models compositional concepts
N Yellinek, L Karlinsky, R Giryes - arXiv preprint arXiv:2312.17345, 2023 - arxiv.org
Vision-Language models (VLMs) have proved effective at aligning image and text
representations, producing superior zero-shot results when transferred to many downstream …
representations, producing superior zero-shot results when transferred to many downstream …
Learning Interpretable Queries for Explainable Image Classification with Information Pursuit
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a
sequence of interpretable queries about the data in order of information gain, updating its …
sequence of interpretable queries about the data in order of information gain, updating its …
Interpretable classifiers based on time-series motifs for lane change prediction
K Klein, O De Candido… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this article, we address the problem of using non-interpretable Machine Learning (ML)
algorithms in safety critical applications, especially automated driving functions. We focus on …
algorithms in safety critical applications, especially automated driving functions. We focus on …
Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosis
Due to the high stakes in medical decision-making, there is a compelling demand for
interpretable deep learning methods in medical image analysis. Concept Bottleneck Models …
interpretable deep learning methods in medical image analysis. Concept Bottleneck Models …