Visual question answering from another perspective: CLEVR mental rotation tests *

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.

This work proposes a transfer learning-based encoder-decoder framework to predict the relationship between loading conditions and residual stiffness in carbon fiber reinforced composites and adhesives. The encoder, built from a Convolutional Neural Network ...

Blind use patterns significantly impact visual comfort and energy efficiency in office buildings. To quantify this impact on building performance, blind control occupant behaviour models (BC-OBMs) are typically integrated into building performance simulati ...

The 'density limit' is one of the fundamental bounds on tokamak operating space, and is commonly estimated via the empirical Greenwald scaling. This limit has garnered renewed interest in recent years as it has become clear that ITER and many tokamak pilot ...

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Neural decoding of the visual system is a subject of research interest, both to understand how the visual system works and to be able to use this knowledge in areas, such as computer vision or brain-computer interfaces. Spike-based decoding is often used, ...

Functional connectivity (FC) between brain regions as manifested via fMRI entails signatures that can be used to differentiate individuals and decode cognitive tasks. In this work, we use methods from graph structure inference to estimate FC, which is in c ...

In recent years statistical physics has proven to be a valuable tool to probe into large dimensional inference problems such as the ones occurring in machine learning. Statistical physics provides analytical tools to study fundamental limitations in their ...

Topographical disorientation refers to the selective inability to orient oneself in familiar surroundings. However, to date its neural correlates remain poorly understood. Here we use quantitative lesion analysis and a lesion network mapping approach in or ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Deep neural networks provide magnificent results for vision tasks. However, their complex structures and numerous parameters make them computationally and memory-wise intensive. Execution of these models on resource-constrained, camera-equipped devices suc ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Visual question answering from another perspective: CLEVR mental rotation tests *

Chattez avec Graph Search

Transfer learning-based approach for evaluating residual stiffness in carbon fiber reinforced composites and adhesives

Development of a blind control occupant behaviour model (BC-OBM) based on contextual and time-related factors through supervised machine learning approaches

Correlation of the L-mode density limit with edge collisionality

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Aggregating Spatial and Photometric Context for Photometric Stereo

Predicting Visual Stimuli From Cortical Response Recorded With Wide-Field Imaging in a Mouse

Joint Subject-Identification and Task-Decoding From Inferred Functional Brain Graphs Via a Multi-Task Neural Network

Sparse representations, inference and learning

The neural correlates of topographical disorientation-a lesion analysis study

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Enabling Uncertainty Estimation in Iterative Neural Networks

Smart Edge for Hierarchical Vision Systems

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Sparse autoregressive neural networks for classical spin systems

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Safe Deep Neural Networks

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights