ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

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.

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 ...

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, ...

Self-organization and emergent behavior lie at the core of many natural phenomena, from pattern formation in biological tissues to the collective motion of flocking birds. Harnessing these principles in computational models can unlock powerful approaches f ...

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 ...

Implanted medical devices (IMDs) have been widely developed to support the monitoring and recording of biological data inside the body or brain. Wirelessly powered IMDs, a subset of implantable electronics, have been proposed to eliminate the limitations r ...

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 ...

Deep neural networks (DNNs) are increasingly proposed as models of human vision, bolstered by their impressive performance on image classification and object recognition tasks. Yet, the extent to which DNNs capture fundamental aspects of human vision such ...

The use of meteorological radars to study snowfall microphysical properties and processes is well established, in particular via a few distinct techniques: the use of radar polarimetry, of multi-frequency radar measurements, and of the radar Doppler spectr ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

Key-Value Stores (KVS) are foundational infrastructure components for online services. Due to their latency-critical nature, today’s best-performing KVS contain a plethora of full-stack optimizations commonly targeting read-mostly, popularity-skewed worklo ...

Cycles are one of the fundamental subgraph patterns and being able to enumerate them in graphs enables important applications in a wide variety of fields, including finance, biology, chemistry, and network science. However, to enable cycle enumeration in r ...

Intracranial hemorrhage (ICH) is a common finding in traumatic brain injury (TBI) and computed tomography (CT) is considered the gold standard for diagnosis. Automated detection of ICH provides clinical value in diagnostics and in the ability to feed robus ...

The need to produce more sustainable concrete is proving imminent given the rising environmental concerns facing the industry. Blended cement concrete, based on any of the prominent supplementary cementitious materials (SCMs) such as fly ash, ground granul ...

Background A variety of imaging methods are available to obtain kinematic data at an interface, with a widely varying range of spatial and temporal resolution. These methods require a trade-off between imaging rate and resolution. Objective A deep learning ...

In this paper, we propose and compare personalized models for Productive Engagement (PE) recognition. PE is defined as the level of engagement that maximizes learning. Previously, in the context of robot-mediated collaborative learning, a framework of prod ...

We present a general framework for portfolio risk management in discrete time, based on a replicating martingale. This martingale is learned from a finite sample in a supervised setting. Our method learns the features necessary for an effective low-dimensi ...

The concerns for climate change and the transition to renewables is increasing the relevance of superconducting applications: High Temperature Superconductor (HTS) cables for efficient power transmission, superconducting magnets for nuclear fusion, superco ...

We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...

We propose a novel machine learning (ML)-driven methodology to estimate biomechanical variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) modeling. MSK models facilitate personalized modeling, perform "what-if" analyses, ...

We present a search for galaxy-scale strong gravitational lenses in the initial 2500 square degrees of the Canada-France Imaging Survey (CFIS). We designed a convolutional neural network (CNN) committee that we applied to a selection of 2 344 002 r-band im ...

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

Chat with Graph Search

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

Dependable learning and control through Neural ODEs

Texture Synthesis using Neural Cellular Automata

Deterministic equivalent and error universality of deep random features learning

Integrated Wireless Power, Data Communication, and Thermal Sensing System for Autonomous Multisite Brain Implants

Multi-Agent Learning in Contextual Games under Unknown Constraints

Divergences in color perception between deep neural networks and humans

Dual-frequency spectral radar retrieval of snowfall microphysics: a physics-driven deep-learning approach

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Cooperative Concurrency Control for Write-Intensive Key-Value Workloads

Fast Parallel Algorithms for Enumeration of Simple, Temporal, and Hop-constrained Cycles

Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans

Data-driven optimization tool for the functional, economic, and environmental properties of blended cement concrete using supplementary cementitious materials

High Resolution Interferometric Imaging of Liquid-Solid Interfaces with HOTNNET

Personalized Productive Engagement Recognition in Robot-Mediated Collaborative Learning

A machine learning approach to portfolio pricing and risk management for high-dimensional problems

A fibre optic and machine learning based health monitoring system for superconducting power applications in modern supergrids

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

Machine Learning for Musculoskeletal Modeling of Upper Extremity

Strong lensing in UNIONS: Toward a pipeline from discovery to modeling