activity
20152019
most citedConstrained deep neural network architecture search for IoT devices accounting hardware calibration

7 citations · 15 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG20197 cited

Constrained deep neural network architecture search for IoT devices accounting hardware calibration

Florian Scheidegger, Luca Benini, Costas Bekas +1

Deep neural networks achieve outstanding results in challenging image classification tasks. However, the design of network topologies is a complex task and the research community m…

cs.LG20196 cited

NeuNetS: An Automated Synthesis Engine for Neural Network Design

Atin Sood, Benjamin Elder, Benjamin Herta +17

Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through AP…

cs.LG2018

TAPAS: Train-less Accuracy Predictor for Architecture Search

R. Istrate, F. Scheidegger, G. Mariani +3

In recent years an increasing number of researchers and practitioners have been suggesting algorithms for large-scale neural network architecture search: genetic algorithms, reinfo…

cs.DL2018

Corpus Conversion Service: A Machine Learning Platform to Ingest Documents at Scale

Peter W J Staar, Michele Dolfi, Christoph Auer +1

Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can…

cs.DL2018

Corpus Conversion Service: A machine learning platform to ingest documents at scale [Poster abstract]

Peter W J Staar, Michele Dolfi, Christoph Auer +1

Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can…

cs.LG2018

Incremental Training of Deep Convolutional Neural Networks

Roxana Istrate, Adelmo Cristiano Innocenza Malossi, Costas Bekas +1

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training p…