15 citations · 19 across the 6 of their papers we have counts for
5 papers · 1 filter
Linear-Time Non-Local Codec Placement for Machine Learning Model Compression
Matteo Spallanzani
On-device inference imposes constraints on model storage and operand traffic and thus benefits from compressed operand representations, which mandate the use of encoding and decodi…
Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering
Thorir Mar Ingolfsson, Mark Vero, Xiaying Wang +3
The computational demands of neural architecture search (NAS) algorithms are usually directly proportional to the size of their target search spaces. Thus, limiting the search to h…
Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Matteo Spallanzani, Gian Paolo Leonardi, Luca Benini
Training quantised neural networks (QNNs) is a non-differentiable optimisation problem since weights and features are output by piecewise constant functions. The standard solution…
Analytical aspects of non-differentiable neural networks
Gian Paolo Leonardi, Matteo Spallanzani
Research in computational deep learning has directed considerable efforts towards hardware-oriented optimisations for deep neural networks, via the simplification of the activation…
Additive Noise Annealing and Approximation Properties of Quantized Neural Networks
Matteo Spallanzani, Lukas Cavigelli, Gian Paolo Leonardi +2
We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural network…