Laboratory of Intelligent Systems

Laboratory

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 this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

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, ...

Navigation of drones is predominantly based on sensor fusion algorithms. Most of these algorithms make use of some form of Bayesian filtering with a majority employing an Extended Kalman Filter (EKF), wherein inertial measurements are fused with a Global N ...

Controlling complex tasks in robotic systems, such as circular motion for cleaning or following curvy lines, can be dealt with using nonlinear vector fields. This article introduces a novel approach called the rotational obstacle avoidance method (ROAM) fo ...

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 ...

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 ...

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 ...

Dielectric Elastomer Actuators (DEAs) have emerged as versatile and promising devices for a multitude of applications, including soft robotics, haptic interfaces, and artificial muscles. DEAs are an interesting soft actuator technology due to their high en ...

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 ...

In recent years, soft robotics has surged in applications like wearables, drones, smart fabrics, and medical instruments. Due to their compliance, these devices excel in tasks demanding dexterity and adaptability, such as manipulation, locomotion, crash re ...

Laboratory of Intelligent Systems

Chat with Graph Search

Deep Learning Theory Through the Lens of Diagonal Linear Networks

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

VDMNav: Software Architecture for Aerodynamically Constrained Navigation on Small Fixed-Wing Drones

Avoidance of Concave Obstacles Through Rotation of Nonlinear Dynamics

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

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Safe Deep Neural Networks

Frequency response of fiber reinforced DEAs

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

Filiform Variable Stiffness Technologies for Medical Robotics