Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

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.

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 ...

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 ...

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 ...

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 ...

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 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 ...

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 ...

We investigate popular resampling methods for estimating the uncertainty of statistical models, such as subsampling, bootstrap and the jackknife, and their performance in high-dimensional supervised regression tasks. We provide a tight asymptotic descripti ...

Hyperdimensional (HD) computing is a novel approach to machine learning inspired by neuroscience, which uses vectors in a hyper-dimensional space to represent data and models. This approach has gained significant interest in recent years with applications ...

Humans and animals constantly adapt to their environment over the course of their life. This thesis seeks to integrate various timescales of adaptation, ranging from the adaptation of synaptic connections between spiking neurons (milliseconds), rapid behav ...

Natural disasters, such as earthquakes, have always represented a danger to human life. Seismic risk assessment consists of the evaluation of existing buildings and their expected response in case of an earthquake; the exposure model of buildings plays a k ...

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...

This work aims to study the effects of wind uncertainties in civil engineering structural design. Optimising the design of a structure for safety or operability without factoring in these uncertainties can result in a design that is not robust to these per ...

Learning journals are increasingly used in vocational education to foster self-regulated learning and reflective learning practices. However, for many apprentices, documenting working experiences is a difficult task. In this paper, we profile apprentices' ...

Classic image-restoration algorithms use a variety of priors, either implicitly or explicitly. Their priors are hand-designed and their corresponding weights are heuristically assigned. Hence, deep learning methods often produce superior image restoration ...

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show that data heteroge ...

Nowadays, image and video are the data types that consume most of the resources of modern communication channels, both in fixed and wireless networks. Thus, it is vital to compress visual data as much as possible, while maintaining some target quality leve ...

The emergence of digital technology is changing education in many ways. A particularly interesting aspect of this transformation is the development of learning environments that can automatically adapt to individual students and can collect data in order t ...

The use of robots in search and rescue is gaining particular interest, but singular skills are required to ensure efficient deployments in real missions. To face this problem, there is a need to develop more intuitive control interfaces. Moreover, to ensur ...

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

Chat with Graph Search

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

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

Learning to Assemble with Alternative Plans

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

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

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

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

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression

Hyperdimensional computing for biosignal monitoring: Applications for epilepsy detection

From event-based surprise to lifelong learning. A journey in the timescales of adaptation

Building typological classification in Switzerland using deep learning methods for seismic assessment

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation

Evolutionary Clustering of Apprentices' Self- Regulated Learning Behavior in Learning Journals

BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

Counting People by Estimating People Flows

Implicit Gradient Alignment in Distributed and Federated Learning

Learning-based Image Coding: Early Solutions Reviewing and Subjective Quality Evaluation

Learning Analytics for Adaptive and Self-Improving Learning Environments for Inductive Teaching

Wearable and Self-Aware Machine Learning System for Online Cognitive Workload Monitoring and Drone Control