Reinforced Attention for Few-Shot Learning and Beyond

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In preparation for error field (EF) identification experiments in ITER, a series of experiments have been conducted at JET to test the portability of the non-disruptive compass scan, a method originally designed and tested in DIII-D (Paz-Soldan et al 2022 ...

Coded aperture imaging is an emerging technique allowing thin form factor cameras that can be cheaply constructed. Many applications benefit from using such lensless cameras, such as face recognition. We propose a method for face recognition using coded ap ...

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...

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 ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Reinforcement feedback can improve motor learning, but the underlying brain mechanisms remain underexplored. In particular, the causal contribution of specific patterns of oscillatory activity within the human striatum is unknown. To address this question, ...

Machine learning is often cited as a new paradigm in control theory, but is also often viewed as empirical and less intuitive for students than classical model-based methods. This is particularly the case for reinforcement learning, an approach that does n ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

We are constantly bombarded by sensory information and constantly making decisions on how to act. In order to optimally adapt behavior, we must judge which sequences of sensory inputs and actions lead to successful outcomes in specific circumstances. Neuro ...

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

In this chapter, we discuss field experiments in surveys that are conducted with the purpose of learning about expectation formation and the link between expectations and behavior. We begin by reviewing the rationale for conducting experiments within surve ...

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

This paper proposes a safe reinforcement learning algorithm for generation bidding decisions and unit maintenance scheduling in a competitive electricity market environment. In this problem, each unit aims to find a bidding strategy that maximizes its reve ...

Motor learning allows animals, including human beings, to acquire skills that are es-sential for efficient interactions with the environment. This ability to learn new motor skills is of great practical relevance for daily-life activities (such as when lea ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Robustness of medical image classification models is limited by its exposure to the candidate disease classes. Generalized zero shot learning (GZSL) aims at correctly predicting seen and unseen classes and most current GZSL approaches have focused on the s ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

Reinforced Attention for Few-Shot Learning and Beyond

Chat with Graph Search

Lessons Learned Executing the Non-disruptive Compass Scan Method at Jet Towards Error Field Identification Experiments in Iter

Face Recognition Using Lensless Camera

Unveiling the complexity of learning and decision-making

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

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Non-invasive stimulation of the human striatum disrupts reinforcement learning of motor skills

Reinforcement learning approach to control an inverted pendulum: A general framework for educational purposes

Robust Collaborative Learning with Linear Gradient Overhead

Striatal Dopamine Signals and Reward Learning

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Survey experiments on economic expectations

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Estimating and Improving the Robustness of Attributions in Text

Supervised learning and inference of spiking neural networks with temporal coding

Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units

Mechanisms underlying reinforcement learning of motor skills

Transformer Models for Vision

Class Specific Feature Disentanglement and Text Embeddings for Multi-label Generalized Zero Shot CXR Classification

Deep Learning Generalization with Limited and Noisy Labels