Pushmeet Kohli

is this you? claim profile

∙ 0 followers

Principal Scientist and Team Leader at DeepMind

Meta-Learning surrogate models for sequential decision making

Meta-learning methods leverage past experience to learn data-driven indu...

03/28/2019 ∙ by Alexandre Galashov, et al. ∙ 22 ∙ share

read it
Structured agents for physical construction

Physical construction -- the ability to compose objects, subject to phys...

04/05/2019 ∙ by Victor Bapst, et al. ∙ 20 ∙ share

read it
Making sense of sensory input

This paper attempts to answer a central question in unsupervised learnin...

10/05/2019 ∙ by Richard Evans, et al. ∙ 15 ∙ share

read it
Learning to Follow Language Instructions with Adversarial Reward Induction

Recent work has shown that deep reinforcement-learning agents can learn ...

06/05/2018 ∙ by Dzmitry Bahdanau, et al. ∙ 14 ∙ share

read it
Degenerate Feedback Loops in Recommender Systems

Machine learning is used extensively in recommender systems deployed in ...

02/27/2019 ∙ by Ray Jiang, et al. ∙ 14 ∙ share

read it
Verification of Non-Linear Specifications for Neural Networks

Prior work on neural network verification has focused on specifications ...

02/25/2019 ∙ by Chongli Qin, et al. ∙ 14 ∙ share

read it
Analysing Mathematical Reasoning Abilities of Neural Models

Mathematical reasoning---a core ability within human intelligence---pres...

04/02/2019 ∙ by David Saxton, et al. ∙ 14 ∙ share

read it
REGAL: Transfer Learning For Fast Optimization of Computation Graphs

We present a deep reinforcement learning approach to optimizing the exec...

05/07/2019 ∙ by Aditya Paliwal, et al. ∙ 14 ∙ share

read it
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that lear...

04/26/2019 ∙ by Jiayuan Mao, et al. ∙ 12 ∙ share

read it
CLEVRER: CoLlision Events for Video REpresentation and Reasoning

The ability to reason about temporal and causal events from videos lies ...

10/03/2019 ∙ by Kexin Yi, et al. ∙ 12 ∙ share

read it
Branch and Bound for Piecewise Linear Neural Network Verification

The success of Deep Learning and its potential use in many safety-critic...

09/14/2019 ∙ by Rudy Bunel, et al. ∙ 11 ∙ share

read it
Graph Matching Networks for Learning the Similarity of Graph Structured Objects

This paper addresses the challenging problem of retrieval and matching o...

04/29/2019 ∙ by Yujia Li, et al. ∙ 8 ∙ share

read it
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures

This paper addresses the problem of evaluating learning systems in safet...

12/04/2018 ∙ by Jonathan Uesato, et al. ∙ 6 ∙ share

read it
Scaling shared model governance via model splitting

Currently the only techniques for sharing governance of a deep learning ...

12/14/2018 ∙ by Miljan Martic, et al. ∙ 6 ∙ share

read it
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications

Models such as Sequence-to-Sequence and Image-to-Sequence are widely use...

04/26/2019 ∙ by Chenglong Wang, et al. ∙ 6 ∙ share

read it
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities

Medical imaging only indirectly measures the molecular identity of the t...

05/30/2019 ∙ by Simon A. A. Kohl, et al. ∙ 5 ∙ share

read it
Compositional Imitation Learning: Explaining and executing one task at a time

We introduce a framework for Compositional Imitation Learning and Execut...

12/04/2018 ∙ by Thomas Kipf, et al. ∙ 4 ∙ share

read it
Adversarial Robustness through Local Linearization

Adversarial training is an effective methodology for training deep neura...

07/04/2019 ∙ by Chongli Qin, et al. ∙ 3 ∙ share

read it
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation

Neural networks are part of many contemporary NLP systems, yet their emp...

09/03/2019 ∙ by Po-Sen Huang, et al. ∙ 1 ∙ share

read it
Piecewise Linear Neural Network verification: A comparative study

The success of Deep Learning and its potential use in many important saf...

11/01/2017 ∙ by Rudy Bunel, et al. ∙ 0 ∙ share

read it
Neural Program Meta-Induction

Most recently proposed methods for Neural Program Induction work under t...

10/11/2017 ∙ by Jacob Devlin, et al. ∙ 0 ∙ share

read it
TerpreT: A Probabilistic Programming Language for Program Induction

We study machine learning formulations of inductive program synthesis; g...

08/15/2016 ∙ by Alexander L. Gaunt, et al. ∙ 0 ∙ share

read it
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

As a step towards developing zero-shot task generalization capabilities ...

06/15/2017 ∙ by Junhyuk Oh, et al. ∙ 0 ∙ share

read it
Deep API Programmer: Learning to Program with APIs

We present DAPIP, a Programming-By-Example system that learns to program...

04/14/2017 ∙ by Surya Bhupatiraju, et al. ∙ 0 ∙ share

read it
Ensemble Bayesian Optimization

Bayesian Optimization (BO) has been shown to be a very effective paradig...

06/05/2017 ∙ by Zi Wang, et al. ∙ 0 ∙ share

read it
Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Variational autoencoders (VAEs) learn representations of data by jointly...

06/01/2017 ∙ by N. Siddharth, et al. ∙ 0 ∙ share

read it
Summary - TerpreT: A Probabilistic Programming Language for Program Induction

We study machine learning formulations of inductive program synthesis; t...

12/02/2016 ∙ by Alexander L. Gaunt, et al. ∙ 0 ∙ share

read it
Neuro-Symbolic Program Synthesis

Recent years have seen the proposal of a number of neural architectures ...

11/06/2016 ∙ by Emilio Parisotto, et al. ∙ 0 ∙ share

read it
Learning Continuous Semantic Representations of Symbolic Expressions

Combining abstract, symbolic reasoning with continuous neural reasoning ...

11/04/2016 ∙ by Miltiadis Allamanis, et al. ∙ 0 ∙ share

read it
Batched High-dimensional Bayesian Optimization via Structural Kernel Learning

Optimization of high-dimensional black-box functions is an extremely cha...

03/06/2017 ∙ by Zi Wang, et al. ∙ 0 ∙ share

read it
Time-Sensitive Bayesian Information Aggregation for Crowdsourcing Systems

Crowdsourcing systems commonly face the problem of aggregating multiple ...

10/21/2015 ∙ by Matteo Venanzi, et al. ∙ 0 ∙ share

read it
Information Gathering in Networks via Active Exploration

How should we gather information in a network, where each node's visibil...

04/24/2015 ∙ by Adish Singla, et al. ∙ 0 ∙ share

read it
Multi-way Particle Swarm Fusion

This paper proposes a novel MAP inference framework for Markov Random Fi...

12/05/2016 ∙ by Chen Liu, et al. ∙ 0 ∙ share

read it
Deep Multi-Modal Image Correspondence Learning

Inference of correspondences between images from different modalities is...

12/05/2016 ∙ by Chen Liu, et al. ∙ 0 ∙ share

read it
Inducing Interpretable Representations with Variational Autoencoders

We develop a framework for incorporating structured graphical models in ...

11/22/2016 ∙ by N. Siddharth, et al. ∙ 0 ∙ share

read it
Memory-augmented Attention Modelling for Videos

We present a method to improve video description generation by modeling ...

11/07/2016 ∙ by Rasool Fakoor, et al. ∙ 0 ∙ share

read it
Deep disentangled representations for volumetric reconstruction

We introduce a convolutional neural network for inferring a compact dise...

10/12/2016 ∙ by Edward Grant, et al. ∙ 0 ∙ share

read it
Partition-Merge: Distributed Inference and Modularity Optimization

This paper presents a novel meta algorithm, Partition-Merge (PM), which ...

09/24/2013 ∙ by Vincent Blondel, et al. ∙ 0 ∙ share

read it
Multi-dimensional Parametric Mincuts for Constrained MAP Inference

In this paper, we propose novel algorithms for inferring the Maximum a P...

07/30/2013 ∙ by Yongsub Lim, et al. ∙ 0 ∙ share

read it
Efficient Continuous Relaxations for Dense CRF

Dense conditional random fields (CRF) with Gaussian pairwise potentials ...

08/22/2016 ∙ by Alban Desmaison, et al. ∙ 0 ∙ share

read it
Learning to Navigate the Energy Landscape

In this paper, we present a novel and efficient architecture for address...

03/18/2016 ∙ by Julien Valentin, et al. ∙ 0 ∙ share

read it
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

While deep neural networks have led to human-level performance on comput...

03/16/2016 ∙ by Yinda Zhang, et al. ∙ 0 ∙ share

read it
Exact and Approximate Inference in Associative Hierarchical Networks using Graph Cuts

Markov Networks are widely used through out computer vision and machine ...

03/15/2012 ∙ by Chris Russell, et al. ∙ 0 ∙ share

read it
Efficient non-greedy optimization of decision trees

Decision trees and randomized forests are widely used in computer vision...

11/12/2015 ∙ by Mohammad Norouzi, et al. ∙ 0 ∙ share

read it
CO2 Forest: Improved Random Forest by Continuous Optimization of Oblique Splits

We propose a novel algorithm for optimizing multivariate linear threshol...

06/19/2015 ∙ by Mohammad Norouzi, et al. ∙ 0 ∙ share

read it
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

We propose a novel approach to reduce the computational cost of evaluati...

04/30/2015 ∙ by Michael Figurnov, et al. ∙ 0 ∙ share

read it
Memory Bounded Deep Convolutional Networks

In this work, we investigate the use of sparsity-inducing regularizers d...

12/03/2014 ∙ by Maxwell D. Collins, et al. ∙ 0 ∙ share

read it
Consensus Message Passing for Layered Graphical Models

Generative models provide a powerful framework for probabilistic reasoni...

10/27/2014 ∙ by Varun Jampani, et al. ∙ 0 ∙ share

read it
Inverse Graphics with Probabilistic CAD Models

Recently, multiple formulations of vision problems as probabilistic inve...

07/04/2014 ∙ by Tejas D. Kulkarni, et al. ∙ 0 ∙ share

read it
Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions

Structured-output learning is a challenging problem; particularly so bec...

06/23/2014 ∙ by Roman Shapovalov, et al. ∙ 0 ∙ share

read it