Search Results for author:
Found 20 papers, 10 papers with code
Concept Gradient: Concept-based Interpretation Without Linear Assumption
We showed that for a general (potentially non-linear) concept, we can mathematically evaluate how a small change of concept affecting the model's prediction, which leads to an extension of gradient-based interpretation to the concept space.
Faith-Shap: The Faithful Shapley Interaction Index
We show that by additionally requiring the faithful interaction indices to satisfy interaction-extensions of the standard individual Shapley axioms (dummy, symmetry, linearity, and efficiency), we obtain a unique Faithful Shapley Interaction index, which we denote Faith-Shap, as a natural generalization of the Shapley value to interactions.
Human-Centered Concept Explanations for Neural Networks
We start by introducing concept explanations including the class of Concept Activation Vectors (CAV) which characterize concepts using vectors in appropriate spaces of neural activations, and discuss different properties of useful concepts, and approaches to measure the usefulness of concept vectors.
First is Better Than Last for Language Data Influence
However, we observe that since the activation connected to the last layer of weights contains "shared logic", the data influenced calculated via the last layer weights prone to a ``cancellation effect'', where the data influence of different examples have large magnitude that contradicts each other.
Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations
We formalize the desiderata of value functions that respect both the model and the data manifold in a set of axioms and are robust to perturbation on off-manifold regions, and show that there exists a unique value function that satisfies these axioms, which we term the Joint Baseline value function, and the resulting Shapley value the Joint Baseline Shapley (JBshap), and validate the effectiveness of JBshap in experiments.
Evaluations and Methods for Explanation through Robustness Analysis
In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis.
Minimizing FLOPs to Learn Efficient Sparse Representations
Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.
On the (In)fidelity and Sensitivity of Explanations
We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.
On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that aims to infer a complete set of concepts that are additionally encouraged to be interpretable, which addresses the limitations of existing methods on concept explanations.
On Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that considers two additional constraints to encourage the interpretability of the discovered concepts.
DEEP-TRIM: REVISITING L1 REGULARIZATION FOR CONNECTION PRUNING OF DEEP NETWORK
State-of-the-art deep neural networks (DNNs) typically have tens of millions of parameters, which might not fit into the upper levels of the memory hierarchy, thus increasing the inference time and energy consumption significantly, and prohibiting their use on edge devices such as mobile phones.
On the (In)fidelity and Sensitivity for Explanations
We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.
Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching
We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus.
Representer Point Selection for Explaining Deep Neural Networks
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction.
Deep Generative Models for Weakly-Supervised Multi-Label Classification
In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data.
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance.
Order-Free RNN with Visual Attention for Multi-Label Classification
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification.
Learning Deep Latent Spaces for Multi-Label Classification
Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance.
Generative-Discriminative Variational Model for Visual Recognition
In other words, our GDVM casts the supervised learning task as a generative learning process, with data discrimination to be jointly exploited for improved classification.
Automatic Bridge Bidding Using Deep Reinforcement Learning
Existing artificial intelligence systems for bridge bidding rely on and are thus restricted by human-designed bidding systems or features.
