b'IDSIA'

research

∙ 04/23/2019

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

The Differentiable Neural Computer (DNC) can learn algorithmic and quest...

Róbert Csordás, et al. ∙

research

∙ 10/14/2021

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

Despite successes across a broad range of applications, Transformers hav...

Róbert Csordás, et al. ∙

research

∙ 07/19/2021

Reward-Weighted Regression Converges to a Global Optimum

Reward-Weighted Regression (RWR) belongs to a family of widely known ite...

Miroslav Štrupl, et al. ∙

research

∙ 06/03/2022

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

Neural ordinary differential equations (ODEs) have attracted much attent...

Kazuki Irie, et al. ∙

research

∙ 11/29/2018

Learning to Reason with Third-Order Tensor Products

We combine Recurrent Neural Networks with Tensor Product Representations...

Imanol Schlag, et al. ∙

research

∙ 08/26/2021

The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers

Recently, many datasets have been proposed to test the systematic genera...

Róbert Csordás, et al. ∙

research

∙ 08/17/2021

A New Constructive Heuristic driven by Machine Learning for the Traveling Salesman Problem

Recent systems applying Machine Learning (ML) to solve the Traveling Sal...

Umberto Junior Mele, et al. ∙

research

∙ 06/16/2020

Parameter-based Value Functions

Learning value functions off-policy is at the core of modern Reinforceme...

Francesco Faccio, et al. ∙

research

∙ 12/31/2021

Improving Baselines in the Wild

We share our experience with the recently released WILDS benchmark, a co...

Kazuki Irie, et al. ∙

research

∙ 05/13/2022

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

Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL ...

Miroslav Štrupl, et al. ∙

research

∙ 10/11/2019

R-SQAIR: Relational Sequential Attend, Infer, Repeat

Traditional sequential multi-object attention models rely on a recurrent...

Aleksandar Stanić, et al. ∙

research

∙ 10/27/2021

Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization

We consider the task of visually estimating the pose of a human from ima...

Marco Ferri, et al. ∙

research

∙ 11/03/2021

Automatic Embedding of Stories Into Collections of Independent Media

We look at how machine learning techniques that derive properties of ite...

Dylan R. Ashley, et al. ∙

research

∙ 12/31/2021

Training and Generating Neural Networks in Compressed Weight Space

The inputs and/or outputs of some neural nets are weight matrices of oth...

Kazuki Irie, et al. ∙

research

∙ 05/29/2019

Are Disentangled Representations Helpful for Abstract Visual Reasoning?

A disentangled representation encodes information about the salient fact...

Sjoerd van Steenkiste, et al. ∙

research

∙ 07/07/2016

Discovering Boolean Gates in Slime Mould

Slime mould of Physarum polycephalum is a large cell exhibiting rich spa...

Simon Harding, et al. ∙

research

∙ 12/22/2016

Highway and Residual Networks learn Unrolled Iterative Estimation

The past year saw the introduction of new architectures such as Highway ...

Klaus Greff, et al. ∙

research

∙ 02/14/2014

A Clockwork RNN

Sequence prediction and classification are ubiquitous and challenging pr...

Jan Koutnik, et al. ∙

research

∙ 11/19/2015

Binding via Reconstruction Clustering

Disentangled distributed representations of data are desirable for machi...

Klaus Greff, et al. ∙

research

∙ 12/29/2011

Descriptor learning for omnidirectional image matching

Feature matching in omnidirectional vision systems is a challenging prob...

Jonathan Masci, et al. ∙

research

∙ 07/07/2012

Object Recognition with Multi-Scale Pyramidal Pooling Networks

We present a Multi-Scale Pyramidal Pooling Network, featuring a novel py...

Jonathan Masci, et al. ∙

research

∙ 07/06/2012

Multimodal similarity-preserving hashing

We introduce an efficient computational framework for hashing data belon...

Jonathan Masci, et al. ∙

research

∙ 06/21/2016

Tagger: Deep Unsupervised Perceptual Grouping

We present a framework for efficient perceptual inference that explicitl...

Klaus Greff, et al. ∙

research

∙ 03/13/2015

LSTM: A Search Space Odyssey

Several variants of the Long Short-Term Memory (LSTM) architecture for r...

Klaus Greff, et al. ∙

research

∙ 08/11/2017

Neural Expectation Maximization

Many real world tasks such as reasoning and physical interaction require...

Klaus Greff, et al. ∙

research

∙ 09/06/2011

Measuring Intelligence through Games

Artificial general intelligence (AGI) refers to research aimed at tackli...

Tom Schaul, et al. ∙

research

∙ 12/11/2012

A Learning Framework for Morphological Operators using Counter-Harmonic Mean

We present a novel framework for learning morphological operators using ...

Jonathan Masci, et al. ∙

research

∙ 06/22/2011

Natural Evolution Strategies

This paper presents Natural Evolution Strategies (NES), a recent family ...

Daan Wierstra, et al. ∙

research

∙ 05/14/2007

Multi-Dimensional Recurrent Neural Networks

Recurrent neural networks (RNNs) have proved effective at one dimensiona...

Alex Graves, et al. ∙

research

∙ 09/05/2007

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity

I postulate that human or other intelligent agents function or should fu...

Juergen Schmidhuber, et al. ∙

research

∙ 05/15/2001

Market-Based Reinforcement Learning in Partially Observable Worlds

Unlike traditional reinforcement learning (RL), market-based RL is in pr...

Ivo Kwee, et al. ∙

research

∙ 07/31/2002

Optimal Ordered Problem Solver

We present a novel, general, optimally fast, incremental way of searchin...

Juergen Schmidhuber, et al. ∙

research

∙ 11/16/2017

Hindsight policy gradients

Goal-conditional policies allow reinforcement learning agents to pursue ...

Paulo Rauber, et al. ∙

research

∙ 04/30/2014

Deep Learning in Neural Networks: An Overview

In recent years, deep artificial neural networks (including recurrent on...

Juergen Schmidhuber, et al. ∙

research

∙ 09/25/2003

Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements

We present the first class of mathematically rigorous, general, fully se...

Juergen Schmidhuber, et al. ∙

research

∙ 04/13/1999

A Computer Scientist's View of Life, the Universe, and Everything

Is the universe computable? If so, it may be much cheaper in terms of in...

Juergen Schmidhuber, et al. ∙

research

∙ 11/30/2000

Algorithmic Theories of Everything

The probability distribution P from which the history of our universe is...

Juergen Schmidhuber, et al. ∙

research

∙ 06/19/2006

New Millennium AI and the Convergence of History

Artificial Intelligence (AI) has recently become a real formal science: ...

Juergen Schmidhuber, et al. ∙

research

∙ 08/31/2007

2006: Celebrating 75 years of AI - History and Outlook: the Next 25 Years

When Kurt Goedel layed the foundations of theoretical computer science i...

Juergen Schmidhuber, et al. ∙

research

∙ 02/10/2003

The New AI: General & Sound & Relevant for Physics

Most traditional artificial intelligence (AI) systems of the past 50 yea...

Juergen Schmidhuber, et al. ∙

research

∙ 07/11/2014

Deep Networks with Internal Selective Attention through Feedback Connections

Traditional convolutional neural networks (CNN) are stationary and feedf...

Marijn Stollenga, et al. ∙

research

∙ 08/04/2017

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

We present a Lipreading system, i.e. a speech recognition system using o...

Michael Wand, et al. ∙

research

∙ 12/15/2005

Evolino for recurrent support vector machines

Traditional Support Vector Machines (SVMs) need pre-wired finite time wi...

Juergen Schmidhuber, et al. ∙

research

∙ 03/07/2006

Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot

We address the problem of autonomously learning controllers for vision-c...

Viktor Zhumatiy, et al. ∙

research

∙ 09/05/2007

Using Data Compressors to Construct Rank Tests

Nonparametric rank tests for homogeneity and component independence are ...

Daniil Ryabko, et al. ∙

research

∙ 11/28/2001

Gradient-based Reinforcement Planning in Policy-Search Methods

We introduce a learning method called "gradient-based reinforcement plan...

Ivo Kwee, et al. ∙

research

∙ 06/10/2011

A Linear Time Natural Evolution Strategy for Non-Separable Functions

We present a novel Natural Evolution Strategy (NES) variant, the Rank-On...

Yi Sun, et al. ∙

research

∙ 09/26/2012

Efficient Natural Evolution Strategies

Efficient Natural Evolution Strategies (eNES) is a novel alternative to ...

Yi Sun, et al. ∙

research

∙ 12/23/2008

Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, S

I argue that data becomes temporarily interesting by itself to some self...

Juergen Schmidhuber, et al. ∙

research

∙ 08/23/2017

Hierarchical Multinomial-Dirichlet model for the estimation of conditional probability tables

We present a novel approach for estimating conditional probability table...

L. Azzimonti, et al. ∙

IDSIA

Featured Researchers