Search Results for author: Jürgen Schmidhuber

Found 68 papers, 37 papers with code

Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets

1 code implementation13 May 2022 Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh Kumar Srivastava

Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL problems that does not require value functions and uses only supervised learning, where the targets for given inputs in a dataset do not change over time.


Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

no code implementations25 Mar 2022 Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems.

Decision Making

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

1 code implementation24 Feb 2022 Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh K. Srivastava

Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions.

Imitation Learning Offline RL +1

Learning Relative Return Policies With Upside-Down Reinforcement Learning

no code implementations23 Feb 2022 Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber, Rupesh Kumar Srivastava

Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems.


The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention

1 code implementation11 Feb 2022 Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the entire training experience.

Continual Learning Image Classification +1

Improving Baselines in the Wild

1 code implementation31 Dec 2021 Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber

We share our experience with the recently released WILDS benchmark, a collection of ten datasets dedicated to developing models and training strategies which are robust to domain shifts.

Automatic Embedding of Stories Into Collections of Independent Media

1 code implementation3 Nov 2021 Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad, Kory W. Mathewson, Jürgen Schmidhuber

We look at how machine learning techniques that derive properties of items in a collection of independent media can be used to automatically embed stories into such collections.


The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization

1 code implementation14 Oct 2021 Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

Despite progress across a broad range of applications, Transformers have limited success in systematic generalization.

Systematic Generalization

Adaptive Control Flow in Transformers Improves Systematic Generalization

no code implementations ICLR 2022 Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

Despite successes across a broad range of applications, Transformers have limited capability in systematic generalization.

Systematic Generalization

Reward-Weighted Regression Converges to a Global Optimum

1 code implementation19 Jul 2021 Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber

Reward-Weighted Regression (RWR) belongs to a family of widely known iterative Reinforcement Learning algorithms based on the Expectation-Maximization framework.


Bayesian brains and the Rényi divergence

no code implementations12 Jul 2021 Noor Sajid, Francesco Faccio, Lancelot Da Costa, Thomas Parr, Jürgen Schmidhuber, Karl Friston

Under the Bayesian brain hypothesis, behavioural variations can be attributed to different priors over generative model parameters.

Bayesian Inference Variational Inference

Going Beyond Linear Transformers with Recurrent Fast Weight Programmers

4 code implementations NeurIPS 2021 Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber

Transformers with linearised attention (''linear Transformers'') have demonstrated the practical scalability and effectiveness of outer product-based Fast Weight Programmers (FWPs) from the '90s.

Atari Games reinforcement-learning

ImageNet as a Representative Basis for Deriving Generally Effective CNN Architectures

no code implementations16 Mar 2021 Lukas Tuggener, Jürgen Schmidhuber, Thilo Stadelmann

We investigate and improve the representativeness of ImageNet as a basis for deriving generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains.

Image Classification

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling

1 code implementation ICLR 2021 Đorđe Miladinović, Aleksandar Stanić, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann

We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation over baseline convolutional architectures and the state-of-the-art among the models within the same class.

Density Estimation

Linear Transformers Are Secretly Fast Weight Programmers

7 code implementations22 Feb 2021 Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber

We show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early '90s, where a ``slow" neural net learns by gradient descent to program the ``fast weights" of another net through sequences of elementary programming instructions which are additive outer products of self-invented activation patterns (today called keys and values).

Language Modelling Machine Translation +1

Meta Learning Backpropagation And Improving It

no code implementations NeurIPS 2021 Louis Kirsch, Jürgen Schmidhuber

Many concepts have been proposed for meta learning with neural networks (NNs), e. g., NNs that learn to reprogram fast weights, Hebbian plasticity, learned learning rules, and meta recurrent NNs.


On the Binding Problem in Artificial Neural Networks

no code implementations9 Dec 2020 Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Contemporary neural networks still fall short of human-level generalization, which extends far beyond our direct experiences.

Hierarchical Relational Inference

no code implementations7 Oct 2020 Aleksandar Stanić, Sjoerd van Steenkiste, Jürgen Schmidhuber

Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics.

Common Sense Reasoning

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

1 code implementation ICLR 2021 Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber

Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing catastrophic interference, etc.

Systematic Generalization

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

1 code implementation9 Jul 2020 Aditya Ramesh, Paulo Rauber, Jürgen Schmidhuber

An agent in a non-stationary contextual bandit problem should balance between exploration and the exploitation of (periodic or structured) patterns present in its previous experiences.

Multi-Armed Bandits

Parameter-Based Value Functions

1 code implementation ICLR 2021 Francesco Faccio, Louis Kirsch, Jürgen Schmidhuber

We introduce a class of value functions called Parameter-Based Value Functions (PBVFs) whose inputs include the policy parameters.

Continuous Control

Meta-Learning for Recalibration of EMG-Based Upper Limb Prostheses

no code implementations ICML Workshop LifelongML 2020 Krsto Proroković, Michael Wand, Jürgen Schmidhuber

An EMG-based upper limb prosthesis relies on a statistical pattern recognition system to map the EMG signal of residual forearm muscles into the appropriate hand movements.


Training Agents using Upside-Down Reinforcement Learning

7 code implementations5 Dec 2019 Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Jaśkowski, Jürgen Schmidhuber

Many of its general principles are outlined in a companion report; the goal of this paper is to develop a practical learning algorithm and show that this conceptually simple perspective on agent training can produce a range of rewarding behaviors for multiple episodic environments.


Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

2 code implementations15 Oct 2019 Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao

We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure.

Question Answering

R-SQAIR: Relational Sequential Attend, Infer, Repeat

no code implementations11 Oct 2019 Aleksandar Stanić, Jürgen Schmidhuber

Traditional sequential multi-object attention models rely on a recurrent mechanism to infer object relations.

Recurrent Neural Processes

2 code implementations13 Jun 2019 Timon Willi, Jonathan Masci, Jürgen Schmidhuber, Christian Osendorfer

We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models.

Gaussian Processes Time Series

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

no code implementations3 Jun 2019 Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber

In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment.

Systematic Generalization

Learning to Reason with Third Order Tensor Products

1 code implementation NeurIPS 2018 Imanol Schlag, Jürgen Schmidhuber

We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data.

Learning to Reason with Third-Order Tensor Products

1 code implementation29 Nov 2018 Imanol Schlag, Jürgen Schmidhuber

We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data.

Investigating Object Compositionality in Generative Adversarial Networks

no code implementations ICLR 2019 Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly

We present a minimal modification of a standard generator to incorporate this inductive bias and find that it reliably learns to generate images as compositions of objects.

Image Generation Instance Segmentation +2

Recurrent World Models Facilitate Policy Evolution

no code implementations NeurIPS 2018 David Ha, Jürgen Schmidhuber

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations.


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

2 code implementations27 Mar 2018 Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, Thilo Stadelmann

We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object recognition in the context of scene understanding.

General Classification Object Recognition +2

World Models

20 code implementations27 Mar 2018 David Ha, Jürgen Schmidhuber

We explore building generative neural network models of popular reinforcement learning environments.

Car Racing reinforcement-learning


no code implementations ICLR 2018 Imanol Schlag, Jürgen Schmidhuber

We improve previous end-to-end differentiable neural networks (NNs) with fast weight memories.

Neural Expectation Maximization

1 code implementation NeurIPS 2017 Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities.

Highway and Residual Networks learn Unrolled Iterative Estimation

no code implementations22 Dec 2016 Klaus Greff, Rupesh K. Srivastava, Jürgen Schmidhuber

We demonstrate that this viewpoint directly leads to the construction of Highway and Residual networks.

Recurrent Highway Networks

5 code implementations ICML 2017 Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník, Jürgen Schmidhuber

We introduce a novel theoretical analysis of recurrent networks based on Gersgorin's circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell.

Language Modelling

Tagger: Deep Unsupervised Perceptual Grouping

2 code implementations NeurIPS 2016 Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Jürgen Schmidhuber, Harri Valpola

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features.

General Classification

Lipreading with Long Short-Term Memory

no code implementations29 Jan 2016 Michael Wand, Jan Koutník, Jürgen Schmidhuber

Lipreading, i. e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods.

Lipreading Speech Recognition

Binding via Reconstruction Clustering

1 code implementation19 Nov 2015 Klaus Greff, Rupesh Kumar Srivastava, Jürgen Schmidhuber

Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples.

Denoising Representation Learning

Training Very Deep Networks

4 code implementations NeurIPS 2015 Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success.

Image Classification

Highway Networks

3 code implementations3 May 2015 Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber

There is plenty of theoretical and empirical evidence that depth of neural networks is a crucial ingredient for their success.

Language Modelling

LSTM: A Search Space Odyssey

12 code implementations13 Mar 2015 Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber

Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995.

Handwriting Recognition Music Modeling +1

Understanding Locally Competitive Networks

no code implementations5 Oct 2014 Rupesh Kumar Srivastava, Jonathan Masci, Faustino Gomez, Jürgen Schmidhuber

Recently proposed neural network activation functions such as rectified linear, maxout, and local winner-take-all have allowed for faster and more effective training of deep neural architectures on large and complex datasets.

A Clockwork RNN

5 code implementations14 Feb 2014 Jan Koutník, Klaus Greff, Faustino Gomez, Jürgen Schmidhuber

Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs.

General Classification

My First Deep Learning System of 1991 + Deep Learning Timeline 1962-2013

no code implementations19 Dec 2013 Jürgen Schmidhuber

Deep Learning has attracted significant attention in recent years.

Compete to Compute

no code implementations NeurIPS 2013 Rupesh K. Srivastava, Jonathan Masci, Sohrob Kazerounian, Faustino Gomez, Jürgen Schmidhuber

Local competition among neighboring neurons is common in biological neural networks (NNs).

Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification

no code implementations1 Sep 2013 Dan Cireşan, Jürgen Schmidhuber

Our Multi-Column Deep Neural Networks achieve best known recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human performance.

General Classification

Natural Evolution Strategies

1 code implementation22 Jun 2011 Daan Wierstra, Tom Schaul, Tobias Glasmachers, Yi Sun, Jürgen Schmidhuber

This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms.

Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices

no code implementations NeurIPS 2010 Yi Sun, Jürgen Schmidhuber, Faustino J. Gomez

We present a new way of converting a reversible finite Markov chain into a nonreversible one, with a theoretical guarantee that the asymptotic variance of the MCMC estimator based on the non-reversible chain is reduced.

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

no code implementations NeurIPS 2008 Alex Graves, Jürgen Schmidhuber

Offline handwriting recognition---the transcription of images of handwritten text---is an interesting task, in that it combines computer vision with sequence learning.

Handwriting Recognition

Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks

no code implementations NeurIPS 2007 Alex Graves, Marcus Liwicki, Horst Bunke, Jürgen Schmidhuber, Santiago Fernández

On-line handwriting recognition is unusual among sequence labelling tasks in that the underlying generator of the observed data, i. e. the movement of the pen, is recorded directly.

Handwriting Recognition Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.