Autonomous Learning of Internal Dynamic Models for Reaching Tasks

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.

Neural Networks (NNs), renowned for their universal approximation capabilities, have proven well-suited for parametrizing nonlinear control policies and modeling complex processes from available data. However, several NN architectures are physics-agnostic, ...

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the second-order tota ...

Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency ...

We study the glass transition by exploring a broad class of kinetic rules that can significantly modify the normal dynamics of supercooled liquids while maintaining thermal equilibrium. Beyond the usual dynamics of liquids, this class includes dynamics in ...

This manuscript considers the problem of learning a random Gaussian network function using a fully connected network with frozen intermediate layers and trainable readout layer. This problem can be seen as a natural generalization of the widely studied ran ...

We study the statistical mechanics and the equilibrium dynamics of a system of classical Heisenberg spins with frustrated interactions on a d -dimensional simple hypercubic lattice, in the limit of infinite dimensionality d -> infinity . In the analysis we ...

The present invention concerns a pivot comprising two assemblies, namely a central assembly (401) and a peripheral assembly (400). These two assemblies are mobile in rotation relative to each other around an axis of rotation (A). The pivot is characterized ...

We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent’s action needs to belong to a feasible set, but the feasible set is a priori unk ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

The present invention relates to systems and methods for predicting a prognosis of the neuropsychological and/or neuropsychiatric status in a subject based on reports of Minor Hallucination (MH) events in combination with electrophysiological data of the s ...

The diagnosis of sleep disorders is still often based on polysomnography, an in-lab exam allowing experts to perform accurate sleep staging, although this is labor-intensive, expensive, and exposing patients to unusual sleep conditions. A state-of-the-art ...

In this thesis, the aerodynamic challenges in flapping wing flight are addressed. In particular, the effects of different wing kinematics, flexibilities, and planforms on the the leading edge vortex development and aerodynamic performance are investigated. ...

Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learn-ing an optimal feature map is often formulated as a ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

In this thesis, we address the complex issue of collision avoidance in the joint space of robots. Avoiding collisions with both the robot's own body parts and obstacles in the environment is a critical constraint in motion planning and is crucial for ensur ...

With the prevalence of smartphones, watches, and Internet of Things (IoT) devices, the ability to track their positions is becoming increasingly important. For many indoor positioning systems (IPSs), providing an uninterrupted flow of information in real-t ...

A kernel method for estimating a probability density function from an independent and identically distributed sample drawn from such density is presented. Our estimator is a linear combination of kernel functions, the coefficients of which are determined b ...

In this paper, we set the mathematical foundations of the Dynamical Low-Rank Approximation (DLRA) method for stochastic differential equations (SDEs). DLRA aims at approximating the solution as a linear combination of a small number of basis vectors with r ...

This paper proposes a method for the construction of quadratic serendipity element (QSE) shape functions on planar convex and concave polygons. Existing approaches for constructing QSE shape functions are linear combinations of the pair-wise products of ge ...

Reduced-order models are indispensable for multi-query or real-time problems. However, there are still many challenges to constructing efficient ROMs for time-dependent parametrized problems. Using a linear reduced space is inefficient for time-dependent n ...

Autonomous Learning of Internal Dynamic Models for Reaching Tasks

Chat with Graph Search

Dependable learning and control through Neural ODEs

Controlled learning of pointwise nonlinearities in neural-network-like architectures

A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

Testing Theories of the Glass Transition with the Same Liquid but Many Kinetic Rules

Deterministic equivalent and error universality of deep random features learning

Frustrated magnets in the limit of infinite dimensions: Dynamics and disorder-free glass transition

Pivot, process for manufacturing such a pivot, oscillator comprising such a pivot, watch movement and timepiece comprising such an oscillator

Multi-Agent Learning in Contextual Games under Unknown Constraints

Towards Trustworthy Deep Learning for Image Reconstruction

System for predicting a prognosis of the neuropsychological and/or neuropsychiatric status in a subject

PPG-Based Sleep Staging Using SleepPPGNet: Extension to Wearables, Improvements, Limitations

The effects of kinematics, flexibility, and planform on the vortex formation and aerodynamic performance of flapping wing flight

End-to-end kernel learning via generative random Fourier features

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Implicit Distance Functions: Learning and Applications in Robotics

Indoor Real-time localization system design for Internet of Things applications

Density estimation in RKHS with application to Korobov spaces in high dimensions

Dynamical Low-Rank Approximation for Stochastic Differential Equations

Quadratic serendipity element shape functions on general planar polygons

Non-intrusive data-driven reduced-order modeling for time-dependent parametrized problems