Alert button
Picture for Lewis Smith

Lewis Smith

Alert button

Improving Dictionary Learning with Gated Sparse Autoencoders

Add code
Bookmark button
Alert button
Apr 30, 2024
Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda

Viaarxiv icon

Quantifying Uncertainty for Machine Learning Based Diagnostic

Add code
Bookmark button
Alert button
Jul 29, 2021
Owen Convery, Lewis Smith, Yarin Gal, Adi Hanuka

Figure 1 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 2 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 3 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Figure 4 for Quantifying Uncertainty for Machine Learning Based Diagnostic
Viaarxiv icon

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective

Add code
Bookmark button
Alert button
Jun 17, 2021
Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal

Figure 1 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 2 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 3 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Figure 4 for Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Viaarxiv icon

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression

Add code
Bookmark button
Alert button
Feb 22, 2021
Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal

Figure 1 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 2 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 3 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Figure 4 for Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
Viaarxiv icon

Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders

Add code
Bookmark button
Alert button
Nov 17, 2020
Mizu Nishikawa-Toomey, Lewis Smith, Yarin Gal

Figure 1 for Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
Figure 2 for Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
Viaarxiv icon

Capsule Networks -- A Probabilistic Perspective

Add code
Bookmark button
Alert button
Apr 07, 2020
Lewis Smith, Lisa Schut, Yarin Gal, Mark van der Wilk

Figure 1 for Capsule Networks -- A Probabilistic Perspective
Figure 2 for Capsule Networks -- A Probabilistic Perspective
Figure 3 for Capsule Networks -- A Probabilistic Perspective
Figure 4 for Capsule Networks -- A Probabilistic Perspective
Viaarxiv icon

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network

Add code
Bookmark button
Alert button
Mar 04, 2020
Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal

Figure 1 for Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Figure 2 for Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Figure 3 for Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Figure 4 for Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Viaarxiv icon

Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks

Add code
Bookmark button
Alert button
Feb 10, 2020
Sebastian Farquhar, Lewis Smith, Yarin Gal

Figure 1 for Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks
Figure 2 for Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks
Figure 3 for Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks
Figure 4 for Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks
Viaarxiv icon

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks

Add code
Bookmark button
Alert button
Dec 22, 2019
Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G. J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon, Yarin Gal

Figure 1 for A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Figure 2 for A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Figure 3 for A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Figure 4 for A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Viaarxiv icon

Flood Detection On Low Cost Orbital Hardware

Add code
Bookmark button
Alert button
Oct 14, 2019
Gonzalo Mateo-Garcia, Silviu Oprea, Lewis Smith, Josh Veitch-Michaelis, Guy Schumann, Yarin Gal, Atılım Güneş Baydin, Dietmar Backes

Figure 1 for Flood Detection On Low Cost Orbital Hardware
Figure 2 for Flood Detection On Low Cost Orbital Hardware
Figure 3 for Flood Detection On Low Cost Orbital Hardware
Figure 4 for Flood Detection On Low Cost Orbital Hardware
Viaarxiv icon