
Improving Differentiable Neural Computers Through Memory Masking, Deallocation, and Link Distribution Sharpness Control
The Differentiable Neural Computer (DNC) can learn algorithmic and quest...
read it

Learning to Reason with ThirdOrder Tensor Products
We combine Recurrent Neural Networks with Tensor Product Representations...
read it

Parameterbased Value Functions
Learning value functions offpolicy is at the core of modern Reinforceme...
read it

RSQAIR: Relational Sequential Attend, Infer, Repeat
Traditional sequential multiobject attention models rely on a recurrent...
read it

Are Disentangled Representations Helpful for Abstract Visual Reasoning?
A disentangled representation encodes information about the salient fact...
read it

Discovering Boolean Gates in Slime Mould
Slime mould of Physarum polycephalum is a large cell exhibiting rich spa...
read it

Highway and Residual Networks learn Unrolled Iterative Estimation
The past year saw the introduction of new architectures such as Highway ...
read it

A Clockwork RNN
Sequence prediction and classification are ubiquitous and challenging pr...
read it

Binding via Reconstruction Clustering
Disentangled distributed representations of data are desirable for machi...
read it

Descriptor learning for omnidirectional image matching
Feature matching in omnidirectional vision systems is a challenging prob...
read it

Object Recognition with MultiScale Pyramidal Pooling Networks
We present a MultiScale Pyramidal Pooling Network, featuring a novel py...
read it

Multimodal similaritypreserving hashing
We introduce an efficient computational framework for hashing data belon...
read it

Tagger: Deep Unsupervised Perceptual Grouping
We present a framework for efficient perceptual inference that explicitl...
read it

LSTM: A Search Space Odyssey
Several variants of the Long ShortTerm Memory (LSTM) architecture for r...
read it

Neural Expectation Maximization
Many real world tasks such as reasoning and physical interaction require...
read it

Measuring Intelligence through Games
Artificial general intelligence (AGI) refers to research aimed at tackli...
read it

A Learning Framework for Morphological Operators using CounterHarmonic Mean
We present a novel framework for learning morphological operators using ...
read it

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

MultiDimensional Recurrent Neural Networks
Recurrent neural networks (RNNs) have proved effective at one dimensiona...
read it

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity
I postulate that human or other intelligent agents function or should fu...
read it

MarketBased Reinforcement Learning in Partially Observable Worlds
Unlike traditional reinforcement learning (RL), marketbased RL is in pr...
read it

Optimal Ordered Problem Solver
We present a novel, general, optimally fast, incremental way of searchin...
read it

Hindsight policy gradients
Goalconditional policies allow reinforcement learning agents to pursue ...
read it

Deep Learning in Neural Networks: An Overview
In recent years, deep artificial neural networks (including recurrent on...
read it

Goedel Machines: SelfReferential Universal Problem Solvers Making Provably Optimal SelfImprovements
We present the first class of mathematically rigorous, general, fully se...
read it

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...
read it

Algorithmic Theories of Everything
The probability distribution P from which the history of our universe is...
read it

New Millennium AI and the Convergence of History
Artificial Intelligence (AI) has recently become a real formal science: ...
read it

2006: Celebrating 75 years of AI  History and Outlook: the Next 25 Years
When Kurt Goedel layed the foundations of theoretical computer science i...
read it

The New AI: General & Sound & Relevant for Physics
Most traditional artificial intelligence (AI) systems of the past 50 yea...
read it

Deep Networks with Internal Selective Attention through Feedback Connections
Traditional convolutional neural networks (CNN) are stationary and feedf...
read it

Improving SpeakerIndependent Lipreading with DomainAdversarial Training
We present a Lipreading system, i.e. a speech recognition system using o...
read it

Evolino for recurrent support vector machines
Traditional Support Vector Machines (SVMs) need prewired finite time wi...
read it

Metric State Space Reinforcement Learning for a VisionCapable Mobile Robot
We address the problem of autonomously learning controllers for visionc...
read it

Using Data Compressors to Construct Rank Tests
Nonparametric rank tests for homogeneity and component independence are ...
read it

Gradientbased Reinforcement Planning in PolicySearch Methods
We introduce a learning method called "gradientbased reinforcement plan...
read it

A Linear Time Natural Evolution Strategy for NonSeparable Functions
We present a novel Natural Evolution Strategy (NES) variant, the RankOn...
read it

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

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...
read it

Hierarchical MultinomialDirichlet model for the estimation of conditional probability tables
We present a novel approach for estimating conditional probability table...
read it

Fitness Uniform Optimization
In evolutionary algorithms, the fitness of a population increases with t...
read it

Fitness Uniform Deletion: A Simple Way to Preserve Diversity
A commonly experienced problem with population based optimisation method...
read it

Statistical comparison of classifiers through Bayesian hierarchical modelling
Usually one compares the accuracy of two competing classifiers via null ...
read it

Desirability and the birth of incomplete preferences
We establish an equivalence between two seemingly different theories: on...
read it

Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis
The machine learning community adopted the use of null hypothesis signif...
read it

Advances in Learning Bayesian Networks of Bounded Treewidth
This work presents novel algorithms for learning Bayesian network struct...
read it

State Space representation of nonstationary Gaussian Processes
The state space (SS) representation of Gaussian processes (GP) has recen...
read it

Should we really use posthoc tests based on meanranks?
The statistical comparison of multiple algorithms over multiple data set...
read it

New Error Bounds for Solomonoff Prediction
Solomonoff sequence prediction is a scheme to predict digits of binary s...
read it

High Degree Sum of Squares Proofs, BienstockZuckerberg hierarchy and ChvatalGomory cuts
ChvatalGomory (CG) cuts and the BienstockZuckerberg hierarchy capture ...
read it
IDSIA
Dalle Molle Institute of Artificial Intelligence Studies is a nonprofit oriented research institute for artificial intelligenc.