Search Results for author: Jürgen Schmidhuber

Found 124 papers, 79 papers with code

Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective

no code implementations9 Jun 2025 Firas Laakom, Haobo Chen, Jürgen Schmidhuber, Yuheng Bu

Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees that fairness achieved during training will generalize to unseen data.

Fairness Generalization Bounds

Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing

1 code implementation1 May 2025 Piotr Piękos, Róbert Csordás, Jürgen Schmidhuber

By selecting $k$ tokens from a sequence of length $T$, MoSA reduces the computational complexity of each attention head from $O(T^2)$ to $O(k^2 + T)$.

Mixture-of-Experts

Can Video Diffusion Model Reconstruct 4D Geometry?

no code implementations27 Mar 2025 Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem

Reconstructing dynamic 3D scenes (i. e., 4D geometry) from monocular video is an important yet challenging problem.

4D reconstruction model +1

Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models

1 code implementation11 Mar 2025 Ruibin Xiong, Yimeng Chen, Dmitrii Khizbullin, Mingchen Zhuge, Jürgen Schmidhuber

In this paper we propose a general agent framework that achieves human-like adaptive writing through recursive task decomposition and dynamic integration of three fundamental task types, i. e. retrieval, reasoning, and composition.

Form Information Retrieval +1

On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers

1 code implementation8 Feb 2025 Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers.

reinforcement-learning Reinforcement Learning

Upside Down Reinforcement Learning with Policy Generators

1 code implementation27 Jan 2025 Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber

Our method, dubbed Upside Down Reinforcement Learning with Policy Generators (UDRLPG), streamlines comparable techniques by removing the need for an evaluator or critic to update the weights of the generator.

reinforcement-learning Reinforcement Learning

How to Correctly do Semantic Backpropagation on Language-based Agentic Systems

1 code implementation4 Dec 2024 Wenyi Wang, Hisham A. Alyahya, Dylan R. Ashley, Oleg Serikov, Dmitrii Khizbullin, Francesco Faccio, Jürgen Schmidhuber

Language-based agentic systems have shown great promise in recent years, transitioning from solving small-scale research problems to being deployed in challenging real-world tasks.

GSM8K

Automatic Album Sequencing

1 code implementation12 Nov 2024 Vincent Herrmann, Dylan R. Ashley, Jürgen Schmidhuber

To address this, we introduce a new user-friendly web-based tool that allows a less technical audience to upload music tracks, execute this technique in one click, and subsequently presents the result in a clean visualization to the user.

FACTS: A Factored State-Space Framework For World Modelling

1 code implementation28 Oct 2024 Li Nanbo, Firas Laakom, Yucheng Xu, Wenyi Wang, Jürgen Schmidhuber

World modelling is essential for understanding and predicting the dynamics of complex systems by learning both spatial and temporal dependencies.

Multivariate Time Series Forecasting State Space Models

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

no code implementations26 Oct 2024 Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan C. Pérez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, Jürgen Schmidhuber, Juan-Manuel Pérez-Rúa

We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework.

Image to Video Generation

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos

1 code implementation17 Jul 2024 Kirolos Ataallah, Xiaoqian Shen, Eslam Abdelrahman, Essam Sleiman, Mingchen Zhuge, Jian Ding, Deyao Zhu, Jürgen Schmidhuber, Mohamed Elhoseiny

This design of the retrieval mechanism enables the Goldfish to efficiently process arbitrarily long video sequences, facilitating its application in contexts such as movies or television series.

Retrieval Video Understanding

Accelerating the inference of string generation-based chemical reaction models for industrial applications

no code implementations12 Jul 2024 Mikhail Andronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber, Djork-Arné Clevert

Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-art accuracy.

Prediction Retrosynthesis +2

Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning

no code implementations12 Jun 2024 Yuhui Wang, Qingyuan Wu, Weida Li, Dylan R. Ashley, Francesco Faccio, Chao Huang, Jürgen Schmidhuber

The Value Iteration Network (VIN) is an end-to-end differentiable architecture that performs value iteration on a latent MDP for planning in reinforcement learning (RL).

Reinforcement Learning (RL)

Highway Value Iteration Networks

no code implementations5 Jun 2024 Yuhui Wang, Weida Li, Francesco Faccio, Qingyuan Wu, Jürgen Schmidhuber

To address this problem, we embed highway value iteration -- a recent algorithm designed to facilitate long-term credit assignment -- into the structure of VINs.

Diversity Safe Exploration

Highway Reinforcement Learning

no code implementations28 May 2024 Yuhui Wang, Miroslav Strupl, Francesco Faccio, Qingyuan Wu, Haozhe Liu, Michał Grudzień, Xiaoyang Tan, Jürgen Schmidhuber

We show, however, that such IS-free methods underestimate the optimal value function (VF), especially for large $n$, restricting their capacity to efficiently utilize information from distant future time steps.

Q-Learning reinforcement-learning +2

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

1 code implementation27 May 2024 Anand Gopalakrishnan, Aleksandar Stanić, Jürgen Schmidhuber, Michael Curtis Mozer

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures.

Object Object Discovery

MoEUT: Mixture-of-Experts Universal Transformers

1 code implementation25 May 2024 Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber, Christopher Potts, Christopher D. Manning

The resulting UT model, for the first time, slightly outperforms standard Transformers on language modeling tasks such as BLiMP and PIQA, while using significantly less compute and memory.

Language Modeling Language Modelling +1

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

1 code implementation6 May 2024 Aditya A. Ramesh, Kenny Young, Louis Kirsch, Jürgen Schmidhuber

Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes.

Chunking Navigate +2

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable

no code implementations1 May 2024 Haozhe Liu, Wentian Zhang, Bing Li, Bernard Ghanem, Jürgen Schmidhuber

Foundational generative models should be traceable to protect their owners and facilitate safety regulation.

Towards a Robust Soft Baby Robot With Rich Interaction Ability for Advanced Machine Learning Algorithms

1 code implementation11 Apr 2024 Mohannad Alhakami, Dylan R. Ashley, Joel Dunham, Yanning Dai, Francesco Faccio, Eric Feron, Jürgen Schmidhuber

Advanced machine learning algorithms require platforms that are extremely robust and equipped with rich sensory feedback to handle extensive trial-and-error learning without relying on strong inductive biases.

Language Agents as Optimizable Graphs

2 code implementations26 Feb 2024 Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jürgen Schmidhuber

Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases.

Prompt Engineering

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

1 code implementation5 Feb 2024 Qingyuan Wu, Simon Sinong Zhan, YiXuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Jürgen Schmidhuber, Chao Huang

To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments.

reinforcement-learning Reinforcement Learning +1

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention

2 code implementations13 Dec 2023 Róbert Csordás, Piotr Piękos, Kazuki Irie, Jürgen Schmidhuber

Our novel SwitchHead is an effective MoE method for the attention layer that successfully reduces both the compute and memory requirements, achieving wall-clock speedup, while matching the language modeling performance of the baseline Transformer.

Language Modeling Language Modelling +1

Automating Continual Learning

1 code implementation1 Dec 2023 Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments.

Continual Learning image-classification +3

Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation

no code implementations14 Nov 2023 Lukas Tuggener, Thilo Stadelmann, Jürgen Schmidhuber

Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances.

Data Augmentation Semantic Segmentation

Unsupervised Musical Object Discovery from Audio

1 code implementation13 Nov 2023 Joonsu Gha, Vincent Herrmann, Benjamin Grewe, Jürgen Schmidhuber, Anand Gopalakrishnan

Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition.

Object Object Discovery +1

Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions

1 code implementation24 Oct 2023 Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

Recent studies of the computational power of recurrent neural networks (RNNs) reveal a hierarchy of RNN architectures, given real-time and finite-precision assumptions.

Approximating Two-Layer Feedforward Networks for Efficient Transformers

2 code implementations16 Oct 2023 Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

Unlike prior work that compares MoEs with dense baselines under the compute-equal condition, our evaluation condition is parameter-equal, which is crucial to properly evaluate LMs.

Learning to Identify Critical States for Reinforcement Learning from Videos

1 code implementation ICCV 2023 Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber

Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions.

Deep Reinforcement Learning reinforcement-learning

Exploring the Promise and Limits of Real-Time Recurrent Learning

1 code implementation30 May 2023 Kazuki Irie, Anand Gopalakrishnan, Jürgen Schmidhuber

To scale to such challenging tasks, we focus on certain well-known neural architectures with element-wise recurrence, allowing for tractable RTRL without approximation.

Diagnostic

Large Language Model Programs

no code implementations9 May 2023 Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li

In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples.

Language Modeling Language Modelling +3

Accelerating Neural Self-Improvement via Bootstrapping

1 code implementation2 May 2023 Kazuki Irie, Jürgen Schmidhuber

Few-shot learning with sequence-processing neural networks (NNs) has recently attracted a new wave of attention in the context of large language models.

Few-Shot Learning

Self-Organising Neural Discrete Representation Learning à la Kohonen

1 code implementation15 Feb 2023 Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

Unsupervised learning of discrete representations in neural networks (NNs) from continuous ones is essential for many modern applications.

Representation Learning

Guiding Online Reinforcement Learning with Action-Free Offline Pretraining

1 code implementation30 Jan 2023 Deyao Zhu, Yuhui Wang, Jürgen Schmidhuber, Mohamed Elhoseiny

In this paper, we investigate the potential of using action-free offline datasets to improve online reinforcement learning, name this problem Reinforcement Learning with Action-Free Offline Pretraining (AFP-RL).

Offline RL reinforcement-learning +2

Eliminating Meta Optimization Through Self-Referential Meta Learning

no code implementations29 Dec 2022 Louis Kirsch, Jürgen Schmidhuber

We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing.

Meta-Learning

Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks

no code implementations29 Dec 2022 Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber

There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions.

On Narrative Information and the Distillation of Stories

1 code implementation22 Nov 2022 Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad, Jürgen Schmidhuber

We then demonstrate how evolutionary algorithms can leverage this to extract a set of narrative templates and how these templates -- in tandem with a novel curve-fitting algorithm we introduce -- can reorder music albums to automatically induce stories in them.

Contrastive Learning Evolutionary Algorithms

Exploring through Random Curiosity with General Value Functions

1 code implementation18 Nov 2022 Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Furthermore, RC-GVF significantly outperforms previous methods in the absence of ground-truth episodic counts in the partially observable MiniGrid environments.

Efficient Exploration

Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks

no code implementations17 Nov 2022 Kazuki Irie, Jürgen Schmidhuber

Short-term memory in standard, general-purpose, sequence-processing recurrent neural networks (RNNs) is stored as activations of nodes or "neurons."

The Benefits of Model-Based Generalization in Reinforcement Learning

1 code implementation4 Nov 2022 Kenny Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber

First, we provide a simple theorem motivating how learning a model as an intermediate step can narrow down the set of possible value functions more than learning a value function directly from data using the Bellman equation.

Model-based Reinforcement Learning reinforcement-learning +2

CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations

1 code implementation12 Oct 2022 Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

While the original CTL is used to test length generalization or productivity, CTL++ is designed to test systematicity of NNs, that is, their capability to generalize to unseen compositions of known functions.

Diagnostic

Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules

1 code implementation7 Oct 2022 Kazuki Irie, Jürgen Schmidhuber

Work on fast weight programmers has demonstrated the effectiveness of key/value outer product-based learning rules for sequentially generating a weight matrix (WM) of a neural net (NN) by another NN or itself.

Denoising Image Generation +1

Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter

1 code implementation5 Aug 2022 Aleksandar Stanić, Yujin Tang, David Ha, Jürgen Schmidhuber

We show that current agents struggle to generalize, and introduce novel object-centric agents that improve over strong baselines.

Meta-Learning

General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States

1 code implementation4 Jul 2022 Francesco Faccio, Aditya Ramesh, Vincent Herrmann, Jean Harb, Jürgen Schmidhuber

In continuous control problems with infinitely many states, our value function minimizes its prediction error by simultaneously learning a small set of `probing states' and a mapping from actions produced in probing states to the policy's return.

continuous-control Continuous Control +2

Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules

2 code implementations3 Jun 2022 Kazuki Irie, Francesco Faccio, Jürgen Schmidhuber

Neural ordinary differential equations (ODEs) have attracted much attention as continuous-time counterparts of deep residual neural networks (NNs), and numerous extensions for recurrent NNs have been proposed.

Time Series Time Series Analysis +1

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.

reinforcement-learning Reinforcement Learning (RL)

Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

1 code implementation25 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.

All Imitation Learning +3

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 Form +3

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.

ARC TAG

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.

ListOps 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.

regression Reinforcement Learning (RL)

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

5 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 ListOps

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.

Decoder Density Estimation

Is it enough to optimize CNN architectures on ImageNet?

1 code implementation16 Mar 2021 Lukas Tuggener, Jürgen Schmidhuber, Thilo Stadelmann

In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains.

image-classification Image Classification

Linear Transformers Are Secretly Fast Weight Programmers

9 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 +2

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.

Meta-Learning

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 Nonstationary Contextual Bandits

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

An agent in a nonstationary 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 Continuous Control +1

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.

Meta-Learning

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.

reinforcement-learning Reinforcement Learning +1

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

3 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.

Math 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.

Inductive Bias Object

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 State Space Models +2

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 Inductive Bias +5

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.

reinforcement-learning Reinforcement Learning +1

World Models

22 code implementations27 Mar 2018 David Ha, Jürgen Schmidhuber

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

Car Racing reinforcement-learning +2

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 +3

GATED FAST WEIGHTS FOR ASSOCIATIVE RETRIEVAL

no code implementations ICLR 2018 Imanol Schlag, Jürgen Schmidhuber

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

Retrieval

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.

Clustering

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

6 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 Modeling 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 Segmentation

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 +1

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.

Clustering Denoising +1

Training Very Deep Networks

3 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

4 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

17 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.

Retrieval

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

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

Measuring Intelligence through Games

no code implementations6 Sep 2011 Tom Schaul, Julian Togelius, Jürgen Schmidhuber

Artificial general intelligence (AGI) refers to research aimed at tackling the full problem of artificial intelligence, that is, create truly intelligent agents.

Motion Planning

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.

Evolutionary Algorithms global-optimization

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 Modeling +1

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