Context selectivity with dynamic availability enables lifelong continual learning

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Neurons in the human amygdala and hippocampus are classically thought to encode a person’s identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semanti ...

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

Sign Language conveys information through multiple channels composed of manual (handshape, hand movement) and non-manual (facial expression, mouthing, body posture) components. Sign language assessment involves giving granular feedback to a learner, in ter ...

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

Despite the increasing number of climate and sustainability pledges, knowledge of how to reach those targets within a given system – systems and transformation knowledge – is often lacking. Backcasting can be highly relevant for tackling this transformatio ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an i ...

Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions ...

Human babies have a natural desire to interact with new toys and objects, through which they learn how the world around them works, e.g., that glass shatters when dropped, but a rubber ball does not. When their predictions are proven incorrect, such as whe ...

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting n ...

Animal behaviour alternates between stochastic exploration and goal-directed actions, which are generated by the underlying neural dynamics. Previously, we demonstrated that the compositional Restricted Boltzmann Machine (cRBM) can decompose whole-brain ac ...

Traditional martial arts are treasures of humanity's knowledge and critical carriers of sociocultural memories throughout history. However, such treasured practices have encountered various challenges in knowledge transmission and now feature many entries ...

Geomembrane systems have been used at hydropower plants as rehabilitation and mitigation technology for several decades and are now used worldwide. In the context of planning an energy transition that promotes the sustainable use of water resources for ene ...

Deploying compute-intensive deep neural networks (DNNs) on resource-constrained end devices has become a prominent trend, enabling localized intelligence. However, efficiently deploying these DNNs at scale poses challenges. To address this, extensive resea ...

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

Context selectivity with dynamic availability enables lifelong continual learning

Chattez avec Graph Search

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Learning to Assemble with Alternative Plans

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment

Domain shift, domain adaptation, and generalization: A focus on MRI

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Probing the latent hierarchical structure of data via diffusion models

Carving the transformation pathways to sustainable futures: A novel analytical framework for backcasting in sustainability transitions

Improving the accuracy and interpretability of neural networks for wind power forecasting

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

The Recurrent Temporal Restricted Boltzmann Machine Captures Neural Assembly Dynamics in Whole-brain Activity

Ontology-based Knowledge Representation for Traditional Martial Arts

A comprehensive review on geomembrane systems application in hydropower

RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition

Navigating the Loop: From Control Systems to Neural Networks and Back