14 citations · 21 across the 5 of their papers we have counts for
5 papers
Ising models of deep neural networks
Dusan Stosic, Darko Stosic, Borko Stosic
This work maps deep neural networks to classical Ising spin models, allowing them to be described using statistical thermodynamics. The density of states shows that structures emer…
Distance Metric Learning through Minimization of the Free Energy
Dusan Stosic, Darko Stosic, Teresa B. Ludermir +1
Distance metric learning has attracted a lot of interest for solving machine learning and pattern recognition problems over the last decades. In this work we present a simple appro…
Search Spaces for Neural Model Training
Darko Stosic, Dusan Stosic
While larger neural models are pushing the boundaries of what deep learning can do, often more weights are needed to train models rather than to run inference for tasks. This paper…
Accelerating Sparse Deep Neural Networks
Asit Mishra, Jorge Albericio Latorre, Jeff Pool +5
As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area…
Nonextensive triplets in stock market indices
Dusan Stosic, Darko Stosic, Tatijana Stosic
Stock market indices are one of the most investigated complex systems in econophysics. Here we extend the existing literature on stock markets in connection with nonextensive stati…