On Linear Learning with Manycore Processors

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.

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Machine learning algorithms such as Convolutional Neural Networks (CNNs) are characterized by high robustness towards quantization, supporting small-bitwidth fixed-point arithmetic at inference time with little to no degradation in accuracy. In turn, small ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

The recent rise in interest in point clouds as an imaging modality has motivated standardization groups such as JPEG and MPEG to launch activities aiming at developing compression standards for point clouds. Lossy compression usually introduces visual arti ...

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

FDTD/FEM simulations, strengthened by machine learning, achieve 95.44% optical absorption efficiency in TiO 2 /TiN plasmonic nanocavities for solar energy harvesting. ...

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 ...

Due to its high parallelism, belief propagation (BP)decoding is amenable to high-throughput applications and thusrepresents a promising solution for the ultra-high peak datarate required by future communication systems. To bridge theperformance gap compare ...

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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and req ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

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 ...

Today's continued increase in demand for processing power, despite the slowdown of Moore's law, has led to an increase in processor count, which has resulted in energy consumption and distribution problems. To address this, there is a growing trend toward ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

The use of point clouds as an imaging modality has been rapidly growing, motivating research on compression methods to enable efficient transmission and storage for many applications. While compression standards relying on conven- tional techniques such as ...

On Linear Learning with Manycore Processors

Chattez avec Graph Search

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

DBFS: Dynamic Bitwidth-Frequency Scaling for Efficient Software-defined SIMD

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Subjective performance evaluation of bitrate allocation strategies for MPEG and JPEG Pleno point cloud compression

Domain shift, domain adaptation, and generalization: A focus on MRI

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Machine-learning-empowered FDTD/FEM simulations for predictive solar energy absorption in plasmonic metamaterial nanocavity arrays

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

High-Throughput and Flexible Belief Propagation List Decoder for Polar Codes

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

Robust machine learning for neuroscientific inference

Probing the latent hierarchical structure of data via diffusion models

Random matrix methods for high-dimensional machine learning models

Self-supervised and few-shot learning for robust bioaerosol monitoring

Topics in statistical physics of high-dimensional machine learning

Learning to Assemble with Alternative Plans

Compilation and Design Space Exploration of Dataflow Programs for Heterogeneous CPU-GPU Platforms

Improving the accuracy and interpretability of neural networks for wind power forecasting

Evaluating the effect of sparse convolutions on point cloud compression