Frédéric Odermatt
YOU?
Author Swipe
View article: Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators Open
Analog in-memory computing—a promising approach for energy-efficient acceleration of deep learning workloads—computes matrix-vector multiplications but only approximately, due to nonidealities that often are non-deterministic or nonlinear.…
View article: Cascaded Beam Search: Plug-and-Play Terminology-Forcing For Neural Machine Translation
Cascaded Beam Search: Plug-and-Play Terminology-Forcing For Neural Machine Translation Open
This paper presents a plug-and-play approach for translation with terminology constraints. Terminology constraints are an important aspect of many modern translation pipelines. In both specialized domains and newly emerging domains (such a…
View article: Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators Open
Analog in-memory computing (AIMC) -- a promising approach for energy-efficient acceleration of deep learning workloads -- computes matrix-vector multiplications (MVMs) but only approximately, due to nonidealities that often are non-determi…
View article: Gradient descent-based programming of analog in-memory computing cores
Gradient descent-based programming of analog in-memory computing cores Open
The precise programming of crossbar arrays of unit-cells is crucial for obtaining high matrix-vector-multiplication (MVM) accuracy in analog in-memory computing (AIMC) cores. We propose a radically different approach based on directly mini…
View article: A Large-Scale Ensemble Learning Framework for Demand Forecasting
A Large-Scale Ensemble Learning Framework for Demand Forecasting Open
Time series forecasting is one of the most essential and ubiquitous tasks in\nmany business problems, including demand forecasting and logistics\noptimization. Traditional time series forecasting methods, however, have\nresulted in small m…