H
Hugo Penedones
Publications - 11
Citations - 2384
Hugo Penedones is an academic researcher. The author has contributed to research in topics: Temporal difference learning & Artificial neural network. The author has an hindex of 5, co-authored 9 publications receiving 1269 citations.
Papers
More filters
Journal ArticleDOI
Improved protein structure prediction using potentials from deep learning
Andrew W. Senior,Richard Evans,John M. Jumper,James Kirkpatrick,Laurent Sifre,Tim Green,Chongli Qin,Augustin Žídek,Alexander Nelson,Alex Bridgland,Hugo Penedones,Stig Petersen,Karen Simonyan,Steve Crossan,Pushmeet Kohli,David T. Jones,David T. Jones,David Silver,Koray Kavukcuoglu,Demis Hassabis +19 more
TL;DR: It is shown that a neural network can be trained to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions, and the resulting potential can be optimized by a simple gradient descent algorithm to generate structures without complex sampling procedures.
Journal ArticleDOI
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13).
Andrew W. Senior,Richard Evans,John M. Jumper,James Kirkpatrick,Laurent Sifre,Tim Green,Chongli Qin,Augustin Žídek,Alexander Nelson,Alex Bridgland,Hugo Penedones,Stig Petersen,Karen Simonyan,Steve Crossan,Pushmeet Kohli,David T. Jones,David T. Jones,David Silver,Koray Kavukcuoglu,Demis Hassabis +19 more
TL;DR: AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13, shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation.
Improving Object Classification using Pose Information
TL;DR: This work proposes a method that exploits pose information in order to improve object classification, and investigates both Multi-layer Perceptrons and Convolutional Neural Network architectures, and achieves state-of-the-art results in the challenging NORB dataset.
Posted Content
Adaptive Lambda Least-Squares Temporal Difference Learning
TL;DR: The $\lambda$ selection problem is formalized as a bias-variance trade-off where the solution is the value of $\ lambda$ that leads to the smallest Mean Squared Value Error (MSVE).
Posted Content
Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem
TL;DR: The issue of approximation errors in areas of sharp discontinuities of the value function being further propagated by bootstrap updates is investigated, and empirical evidence of leakage propagation is shown, and analytically it is shown that it must occur, in a simple Markov chain, when function approximation errors are present.