A Framework to Learn with Interpretation
Dec 6, 2021
Speakers
Jayneel Parekh
Speaker · 0 followers
Florence d'Alché-Buc
Speaker · 0 followers
Pavlo Mozharovskyi
Speaker · 0 followers
About
To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive model in terms of human-understandable high level attribute functions, with minimal loss of accuracy. This is achieved by a dedicated architecture and well chosen regularization penalties. We seek for a small-size dictionary of high level attribute functions that take as inputs the outputs of selected hidden layers and whose outputs feed a linear classifier. We impose strong conciseness on the activation of attributes with an entropy-based criterion while enforcing fidelity to both inputs and outputs of the predictive model. A detailed pipeline to visualize the learnt features is also developed. Moreover, besides generating interpretable models by design, our approach can be specialized to provide post-hoc interpretations for a pre-trained neural network. We validate our approach against several state-of-the-art methods on multiple datasets and show its efficacy on both kinds of tasks.To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive model in terms of human-understandable high level attribute functions, with minimal loss of accuracy. This is achieved by a dedicated architecture and well chosen regularization penalties. We seek for a small-size dictionary of high level attribute functions that…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Improving Transferability of Representations via Augmentation-Aware Self-Supervision
Watch later
Hankook Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Autonomous Debris Pile Estimation Challenge
Watch later
Bill Basener, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adversarial Intrinsic Motivation for Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
Watch later
Zhiyuan Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Image Generation using Continuous Filter Atoms
Watch later
Ze Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%