
-
Supermasks in Superposition
We present the Supermasks in Superposition (SupSup) model, capable of se...
read it
-
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
In this paper, we introduce a novel form of value function, Q(s, s'), th...
read it
-
Plug and Play Language Models: a Simple Approach to Controlled Text Generation
Large transformer-based language models (LMs) trained on huge text corpo...
read it
-
First-Order Preconditioning via Hypergradient Descent
Standard gradient descent methods are susceptible to a range of issues t...
read it
-
LCA: Loss Change Allocation for Neural Network Training
Neural networks enjoy widespread use, but many aspects of their training...
read it
-
Hamiltonian Neural Networks
Even though neural networks enjoy widespread use, they still struggle to...
read it
-
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
The recent "Lottery Ticket Hypothesis" paper by Frankle & Carbin showed ...
read it
-
Understanding Neural Networks via Feature Visualization: A survey
A neuroscience method to understanding the brain is to find and study th...
read it
-
Metropolis-Hastings Generative Adversarial Networks
We introduce the Metropolis-Hastings generative adversarial network (MH-...
read it
-
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
Few ideas have enjoyed as large an impact on deep learning as convolutio...
read it
-
Measuring the Intrinsic Dimension of Objective Landscapes
Many recently trained neural networks employ large numbers of parameters...
read it
-
Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning
This is the Proceedings of NIPS 2017 Symposium on Interpretable Machine ...
read it
-
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability
We propose a new technique, Singular Vector Canonical Correlation Analys...
read it
-
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
Generating high-resolution, photo-realistic images has been a long-stand...
read it
-
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Deep neural networks (DNNs) have demonstrated state-of-the-art results o...
read it
-
Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
We can better understand deep neural networks by identifying which featu...
read it
-
Convergent Learning: Do different neural networks learn the same representations?
Recent success in training deep neural networks have prompted active inv...
read it
-
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
Deep neural networks with alternating convolutional, max-pooling and dec...
read it
-
Understanding Neural Networks Through Deep Visualization
Recent years have produced great advances in training large, deep neural...
read it
-
GSNs : Generative Stochastic Networks
We introduce a novel training principle for probabilistic models that is...
read it
-
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Deep neural networks (DNNs) have recently been achieving state-of-the-ar...
read it
-
How transferable are features in deep neural networks?
Many deep neural networks trained on natural images exhibit a curious ph...
read it
-
Hands-free Evolution of 3D-printable Objects via Eye Tracking
Interactive evolution has shown the potential to create amazing and comp...
read it
-
MAV Stabilization using Machine Learning and Onboard Sensors
In many situations, Miniature Aerial Vehicles (MAVs) are limited to usin...
read it