List of works - Jascha Sohl-Dickstein

A Device for Human Ultrasonic Echolocation

scientific article

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans ⬇️

scholarly article by Gamaleldin Elsayed et al published 2018 in Advances in Neural Information Processing Systems 31

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models ⬇️

scientific article published on 9 June 2022

Deep Knowledge Tracing ⬇️

Deep Unsupervised Learning using Nonequilibrium Thermodynamics ⬇️

Dust deposition on the Mars Exploration Rover Panoramic Camera (Pancam) calibration targets

scholarly article

Dust deposition on the decks of the Mars Exploration Rovers: 10 years of dust dynamics on the Panoramic Camera calibration targets.

scientific article published on 23 May 2015

Exponential expressivity in deep neural networks through transient chaos ⬇️

scientific article published in January 2016

Finite Versus Infinite Neural Networks: an Empirical Study ⬇️

scientific article published in November 2020

Invertible Convolutional Flow ⬇️

Modeling higher-order correlations within cortical microcolumns

scientific article

New method for parameter estimation in probabilistic models: minimum probability flow

scientific article published on 21 November 2011

Non-Gaussian statistical properties of breast images

scientific article

Novel local learning rule for neural adaptation fits Hopfield memory networks efficiently and optimally

scientific article published on 8 July 2013

Optogenetic activation of an inhibitory network enhances feedforward functional connectivity in auditory cortex

scientific article

PCA of high dimensional random walks with comparison to neural network training ⬇️

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models ⬇️

scientific article published in January 2017

Radiative transfer modeling of dust-coated Pancam calibration target materials: Laboratory visible/near-infrared spectrogoniometry

scholarly article

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability ⬇️

scientific article published in January 2017

Training sparse natural image models with a fast Gibbs sampler of an extended state space ⬇️

scientific article published in January 2012

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent ⬇️

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling ⬇️

scientific article published in November 2020

List of works by Jascha Sohl-Dickstein

A Device for Human Ultrasonic Echolocation

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans ⬇️

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models ⬇️

Deep Knowledge Tracing ⬇️

Deep Unsupervised Learning using Nonequilibrium Thermodynamics ⬇️

Dust deposition on the Mars Exploration Rover Panoramic Camera (Pancam) calibration targets

Dust deposition on the decks of the Mars Exploration Rovers: 10 years of dust dynamics on the Panoramic Camera calibration targets.

Exponential expressivity in deep neural networks through transient chaos ⬇️

Finite Versus Infinite Neural Networks: an Empirical Study ⬇️

Invertible Convolutional Flow ⬇️

Modeling higher-order correlations within cortical microcolumns

New method for parameter estimation in probabilistic models: minimum probability flow

Non-Gaussian statistical properties of breast images

Novel local learning rule for neural adaptation fits Hopfield memory networks efficiently and optimally

Optogenetic activation of an inhibitory network enhances feedforward functional connectivity in auditory cortex

PCA of high dimensional random walks with comparison to neural network training ⬇️

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models ⬇️

Radiative transfer modeling of dust-coated Pancam calibration target materials: Laboratory visible/near-infrared spectrogoniometry

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability ⬇️

Training sparse natural image models with a fast Gibbs sampler of an extended state space ⬇️

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent ⬇️

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling ⬇️