Search Results for author: Balázs Kégl

Found 19 papers, 3 papers with code

Learning the 2-D Topology of Images

no code implementations NeurIPS 2007 Nicolas L. Roux, Yoshua Bengio, Pascal Lamblin, Marc Joliveau, Balázs Kégl

We study the following question: is the two-dimensional structure of images a very strong prior or is it something that can be learned with a few examples of natural images?

Algorithms for Hyper-Parameter Optimization

no code implementations NeurIPS 2011 James S. Bergstra, Rémi Bardenet, Yoshua Bengio, Balázs Kégl

Random search has been shown to be sufficiently efficient for learning neural networks for several datasets, but we show it is unreliable for training DBNs.

Image Classification

Correlation-based construction of neighborhood and edge features

no code implementations20 Dec 2013 Balázs Kégl

Next, we connect neighborhood features that correlate, and construct edge features by subtracting the correlated neighborhood features of each other.

Multi-class Classification

The return of AdaBoost.MH: multi-class Hamming trees

no code implementations20 Dec 2013 Balázs Kégl

Within the framework of AdaBoost. MH, we propose to train vector-valued decision trees to optimize the multi-class edge without reducing the multi-class problem to $K$ binary one-against-all classifications.

Computational Efficiency

Digits that are not: Generating new types through deep neural nets

no code implementations14 Jun 2016 Akın Kazakçıand Mehdi Cherti, Balázs Kégl

For an artificial creative agent, an essential driver of the search for novelty is a value function which is often provided by the system designer or users.

Similarity encoding for learning with dirty categorical variables

2 code implementations4 Jun 2018 Patricio Cerda, Gaël Varoquaux, Balázs Kégl

We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains.

Dimensionality Reduction

Spurious samples in deep generative models: bug or feature?

no code implementations3 Oct 2018 Balázs Kégl, Mehdi Cherti, Akın Kazakçı

Traditional wisdom in generative modeling literature is that spurious samples that a model can generate are errors and they should be avoided.

InsectUp: Crowdsourcing Insect Observations to Assess Demographic Shifts and Improve Classification

no code implementations30 May 2019 Léonard Boussioux, Tomás Giro-Larraz, Charles Guille-Escuret, Mehdi Cherti, Balázs Kégl

Insects play such a crucial role in ecosystems that a shift in demography of just a few species can have devastating consequences at environmental, social and economic levels.

General Classification

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?

1 code implementation ICLR 2021 Balázs Kégl, Gabriel Hurtado, Albert Thomas

We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent.

Acrobot Model-based Reinforcement Learning

The guide and the explorer: smart agents for resource-limited iterated batch reinforcement learning

no code implementations29 Sep 2021 Albert Thomas, Balázs Kégl, Othman Gaizi, Gabriel Hurtado

Iterated batch reinforcement learning (RL) is a growing subfield fueled by the demand from systems engineers for intelligent control solutions that they can apply within their technical and organizational constraints.

Acrobot Model Predictive Control +1

Knothe-Rosenblatt transport for Unsupervised Domain Adaptation

no code implementations6 Oct 2021 Aladin Virmaux, Illyyne Saffar, Jianfeng Zhang, Balázs Kégl

Knothe-Rosenblatt Domain Adaptation (KRDA) is based on the Knothe-Rosenblatt transport: we exploit autoregressive density estimation algorithms to accurately model the different sources by an autoregressive model using a mixture of Gaussians.

Density Estimation Unsupervised Domain Adaptation

Guided Safe Shooting: model based reinforcement learning with safety constraints

no code implementations20 Jun 2022 Giuseppe Paolo, Jonas Gonzalez-Billandon, Albert Thomas, Balázs Kégl

In the last decade, reinforcement learning successfully solved complex control tasks and decision-making problems, like the Go board game.

Decision Making Model-based Reinforcement Learning +2

Multi-timestep models for Model-based Reinforcement Learning

no code implementations9 Oct 2023 Abdelhakim Benechehab, Giuseppe Paolo, Albert Thomas, Maurizio Filippone, Balázs Kégl

In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data.

Model-based Reinforcement Learning reinforcement-learning +1

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning

no code implementations5 Feb 2024 Abdelhakim Benechehab, Albert Thomas, Balázs Kégl

We consider the problem of offline reinforcement learning where only a set of system transitions is made available for policy optimization.

D4RL Model-based Reinforcement Learning +1

A call for embodied AI

no code implementations6 Feb 2024 Giuseppe Paolo, Jonas Gonzalez-Billandon, Balázs Kégl

We propose Embodied AI as the next fundamental step in the pursuit of Artificial General Intelligence, juxtaposing it against current AI advancements, particularly Large Language Models.

Learning Theory Philosophy

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