Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Jürgen Schmidhuber

Jürgen Schmidhuber

Linear Transformers Are Secretly Fast Weight Memory Systems


Feb 23, 2021
Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber

Figure 1 for Linear Transformers Are Secretly Fast Weight Memory Systems
Figure 2 for Linear Transformers Are Secretly Fast Weight Memory Systems
Figure 3 for Linear Transformers Are Secretly Fast Weight Memory Systems
Figure 4 for Linear Transformers Are Secretly Fast Weight Memory Systems

  Access Paper or Ask Questions

Meta Learning Backpropagation And Improving It


Dec 29, 2020
Louis Kirsch, Jürgen Schmidhuber

Figure 1 for Meta Learning Backpropagation And Improving It
Figure 2 for Meta Learning Backpropagation And Improving It
Figure 3 for Meta Learning Backpropagation And Improving It
Figure 4 for Meta Learning Backpropagation And Improving It

  Access Paper or Ask Questions

On the Binding Problem in Artificial Neural Networks


Dec 09, 2020
Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for On the Binding Problem in Artificial Neural Networks
Figure 2 for On the Binding Problem in Artificial Neural Networks
Figure 3 for On the Binding Problem in Artificial Neural Networks
Figure 4 for On the Binding Problem in Artificial Neural Networks

  Access Paper or Ask Questions

Unsupervised Object Keypoint Learning using Local Spatial Predictability


Nov 25, 2020
Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Unsupervised Object Keypoint Learning using Local Spatial Predictability
Figure 2 for Unsupervised Object Keypoint Learning using Local Spatial Predictability
Figure 3 for Unsupervised Object Keypoint Learning using Local Spatial Predictability
Figure 4 for Unsupervised Object Keypoint Learning using Local Spatial Predictability
* pre-print. under review. 19 pages, 10 figures 
  Access Paper or Ask Questions

Learning Associative Inference Using Fast Weight Memory


Nov 16, 2020
Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber

Figure 1 for Learning Associative Inference Using Fast Weight Memory
Figure 2 for Learning Associative Inference Using Fast Weight Memory
Figure 3 for Learning Associative Inference Using Fast Weight Memory
Figure 4 for Learning Associative Inference Using Fast Weight Memory

  Access Paper or Ask Questions

Hierarchical Relational Inference


Oct 07, 2020
Aleksandar Stanić, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Hierarchical Relational Inference
Figure 2 for Hierarchical Relational Inference
Figure 3 for Hierarchical Relational Inference
Figure 4 for Hierarchical Relational Inference

  Access Paper or Ask Questions

Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks


Oct 05, 2020
Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Figure 2 for Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Figure 3 for Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Figure 4 for Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks

  Access Paper or Ask Questions

Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits


Jul 09, 2020
Aditya Ramesh, Paulo Rauber, Jürgen Schmidhuber

Figure 1 for Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits
Figure 2 for Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits
Figure 3 for Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits
Figure 4 for Recurrent Neural-Linear Posterior Sampling for Non-Stationary Contextual Bandits

  Access Paper or Ask Questions

Parameter-based Value Functions


Jun 16, 2020
Francesco Faccio, Jürgen Schmidhuber

Figure 1 for Parameter-based Value Functions
Figure 2 for Parameter-based Value Functions
Figure 3 for Parameter-based Value Functions
* 24 pages, 67 references 
  Access Paper or Ask Questions

Training Agents using Upside-Down Reinforcement Learning


Dec 05, 2019
Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Jaśkowski, Jürgen Schmidhuber

Figure 1 for Training Agents using Upside-Down Reinforcement Learning
Figure 2 for Training Agents using Upside-Down Reinforcement Learning
Figure 3 for Training Agents using Upside-Down Reinforcement Learning
Figure 4 for Training Agents using Upside-Down Reinforcement Learning
* NNAISENSE Technical Report. 17 pages, 6 figures 
  Access Paper or Ask Questions

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving


Oct 15, 2019
Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao

Figure 1 for Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Figure 2 for Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Figure 3 for Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Figure 4 for Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

  Access Paper or Ask Questions

R-SQAIR: Relational Sequential Attend, Infer, Repeat


Oct 11, 2019
Aleksandar Stanić, Jürgen Schmidhuber

Figure 1 for R-SQAIR: Relational Sequential Attend, Infer, Repeat
Figure 2 for R-SQAIR: Relational Sequential Attend, Infer, Repeat
Figure 3 for R-SQAIR: Relational Sequential Attend, Infer, Repeat
* 4 page workshop paper accepted at the NeurIPS 2019 Workshop on Perception as Generative Reasoning: Structure, Causality, Probability 
  Access Paper or Ask Questions

Improving Generalization in Meta Reinforcement Learning using Learned Objectives


Oct 09, 2019
Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Figure 2 for Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Figure 3 for Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Figure 4 for Improving Generalization in Meta Reinforcement Learning using Learned Objectives

  Access Paper or Ask Questions

Recurrent Neural Processes


Jun 13, 2019
Timon Willi, Jonathan Masci, Jürgen Schmidhuber, Christian Osendorfer

Figure 1 for Recurrent Neural Processes
Figure 2 for Recurrent Neural Processes
Figure 3 for Recurrent Neural Processes
Figure 4 for Recurrent Neural Processes

  Access Paper or Ask Questions

A Perspective on Objects and Systematic Generalization in Model-Based RL


Jun 03, 2019
Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber

Figure 1 for A Perspective on Objects and Systematic Generalization in Model-Based RL
* Accepted to the ICML 2019 workshop on Workshop on Generative Modeling and Model-Based Reasoning for Robotics and AI 
  Access Paper or Ask Questions

Are Disentangled Representations Helpful for Abstract Visual Reasoning?


May 29, 2019
Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber, Olivier Bachem

Figure 1 for Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Figure 2 for Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Figure 3 for Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Figure 4 for Are Disentangled Representations Helpful for Abstract Visual Reasoning?
* This is a preliminary pre-print 
  Access Paper or Ask Questions

Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control


Apr 23, 2019
Róbert Csordás, Jürgen Schmidhuber

Figure 1 for Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
Figure 2 for Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
Figure 3 for Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
Figure 4 for Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control

  Access Paper or Ask Questions

Learning to Reason with Third-Order Tensor Products


Nov 29, 2018
Imanol Schlag, Jürgen Schmidhuber

Figure 1 for Learning to Reason with Third-Order Tensor Products
Figure 2 for Learning to Reason with Third-Order Tensor Products
Figure 3 for Learning to Reason with Third-Order Tensor Products
Figure 4 for Learning to Reason with Third-Order Tensor Products

  Access Paper or Ask Questions

Recurrent World Models Facilitate Policy Evolution


Sep 04, 2018
David Ha, Jürgen Schmidhuber

Figure 1 for Recurrent World Models Facilitate Policy Evolution
Figure 2 for Recurrent World Models Facilitate Policy Evolution
Figure 3 for Recurrent World Models Facilitate Policy Evolution
* To appear at NIPS 2018, selected for an oral presentation. arXiv admin note: substantial text overlap with arXiv:1803.10122 
  Access Paper or Ask Questions

DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects


May 26, 2018
Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, Thilo Stadelmann

Figure 1 for DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects
Figure 2 for DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects
Figure 3 for DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects
Figure 4 for DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects
* 6 pages, accepted on IEEE International Conference on Pattern Recognition 2018 
  Access Paper or Ask Questions

World Models


May 09, 2018
David Ha, Jürgen Schmidhuber

Figure 1 for World Models
Figure 2 for World Models
Figure 3 for World Models
Figure 4 for World Models

  Access Paper or Ask Questions

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions


Feb 28, 2018
Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber

Figure 1 for Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Figure 2 for Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Figure 3 for Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Figure 4 for Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
* Accepted to ICLR 2018 
  Access Paper or Ask Questions

Neural Expectation Maximization


Nov 04, 2017
Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Neural Expectation Maximization
Figure 2 for Neural Expectation Maximization
Figure 3 for Neural Expectation Maximization
Figure 4 for Neural Expectation Maximization
* Accepted to NIPS 2017 
  Access Paper or Ask Questions

LSTM: A Search Space Odyssey


Oct 04, 2017
Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber

Figure 1 for LSTM: A Search Space Odyssey
Figure 2 for LSTM: A Search Space Odyssey
Figure 3 for LSTM: A Search Space Odyssey
Figure 4 for LSTM: A Search Space Odyssey
* IEEE Transactions on Neural Networks and Learning Systems ( Volume: 28, Issue: 10, Oct. 2017 ) Pages: 2222 - 2232 
 * 12 pages, 6 figures 
  Access Paper or Ask Questions

Recurrent Highway Networks


Jul 04, 2017
Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník, Jürgen Schmidhuber

Figure 1 for Recurrent Highway Networks
Figure 2 for Recurrent Highway Networks
Figure 3 for Recurrent Highway Networks
Figure 4 for Recurrent Highway Networks
* 12 pages, 6 figures, 3 tables 
  Access Paper or Ask Questions

Highway and Residual Networks learn Unrolled Iterative Estimation


Mar 14, 2017
Klaus Greff, Rupesh K. Srivastava, Jürgen Schmidhuber

Figure 1 for Highway and Residual Networks learn Unrolled Iterative Estimation
Figure 2 for Highway and Residual Networks learn Unrolled Iterative Estimation
Figure 3 for Highway and Residual Networks learn Unrolled Iterative Estimation
Figure 4 for Highway and Residual Networks learn Unrolled Iterative Estimation
* 10 + 4 pages, accepted for ICLR 2017 
  Access Paper or Ask Questions

Tagger: Deep Unsupervised Perceptual Grouping


Nov 28, 2016
Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Jürgen Schmidhuber, Harri Valpola

Figure 1 for Tagger: Deep Unsupervised Perceptual Grouping
Figure 2 for Tagger: Deep Unsupervised Perceptual Grouping
Figure 3 for Tagger: Deep Unsupervised Perceptual Grouping
Figure 4 for Tagger: Deep Unsupervised Perceptual Grouping
* 14 pages + 5 pages supplementary, accepted at NIPS 2016 
  Access Paper or Ask Questions

Lipreading with Long Short-Term Memory


Jan 29, 2016
Michael Wand, Jan Koutník, Jürgen Schmidhuber

Figure 1 for Lipreading with Long Short-Term Memory
Figure 2 for Lipreading with Long Short-Term Memory
Figure 3 for Lipreading with Long Short-Term Memory
* Accepted for publication at ICASSP 2016 
  Access Paper or Ask Questions

Binding via Reconstruction Clustering


Jan 20, 2016
Klaus Greff, Rupesh Kumar Srivastava, Jürgen Schmidhuber

Figure 1 for Binding via Reconstruction Clustering
Figure 2 for Binding via Reconstruction Clustering
Figure 3 for Binding via Reconstruction Clustering
Figure 4 for Binding via Reconstruction Clustering
* 12 pages, plus 12 pages Appendix 
  Access Paper or Ask Questions