Search Results for author: Jason Liang

Found 7 papers, 3 papers with code

Designing Counterfactual Generators using Deep Model Inversion

no code implementations NeurIPS 2021 Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan, Jason Liang, Akshay Chaudhari, Andreas Spanias

Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models.

Image Generation

Training Stacked Denoising Autoencoders for Representation Learning

no code implementations16 Feb 2021 Jason Liang, Keith Kelly

We implement stacked denoising autoencoders, a class of neural networks that are capable of learning powerful representations of high dimensional data.

Denoising Image Classification +1

Regularized Evolutionary Population-Based Training

no code implementations11 Feb 2020 Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, Risto Miikkulainen

This paper presents an algorithm called Evolutionary Population-Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions.

Knowledge Distillation

Evolutionary Architecture Search For Deep Multitask Networks

no code implementations10 Mar 2018 Jason Liang, Elliot Meyerson, Risto Miikkulainen

Multitask learning, i. e. learning several tasks at once with the same neural network, can improve performance in each of the tasks.

Neural Architecture Search

Cannot find the paper you are looking for? You can Submit a new open access paper.