Optimization of neural network

Bc. Martin BULÍN

Master's thesis

Optimization of neural networks

Abstract:

Neural networks can be trained to work well for particular tasks, but hardly ever we know why they work so well. Due to the complicated architectures and an enormous number of parameters we usually have well-working black-boxes and it is hard if not impossible to make targeted changes in a trained model. In this thesis, we focus on network optimization, specifically we make networks small and simple by removing unimportant synapses, while keeping the classification accuracy of the original fully-connected networks. Based on our experience, at least 90% of the synapses are usually redundant in fully-connected networks. A pruned network consists of important parts only and therefore we can find input-output rules and make statements about individual parts of the network. To identify which synapses are unimportant a new measure is introduced. The methods are presented on six examples, where we show the ability of our pruning algorithm 1) to find a minimal network structure; 2) to select features; 3) to detect patterns among samples; 4) to partially demystify a complicated network; 5) to rapidly reduce the learning and prediction time. The network pruning algorithm is general and applicable for any classification problem.

Abstract:

Neural networks can be trained to work well for particular tasks, but hardly ever we know why they work so well. Due to the complicated architectures and an enormous number of parameters we usually have well-working black-boxes and it is hard if not impossible to make targeted changes in a trained model. In this thesis, we focus on network optimization, specifically we make networks small and simple by removing unimportant synapses, while keeping the classification accuracy of the original fully-connected networks. Based on our experience, at least 90% of the synapses are usually redundant in fully-connected networks. A pruned network consists of important parts only and therefore we can find input-output rules and make statements about individual parts of the network. To identify which synapses are unimportant a new measure is introduced. The methods are presented on six examples, where we show the ability of our pruning algorithm 1) to find a minimal network structure; 2) to select features; 3) to detect patterns among samples; 4) to partially demystify a complicated network; 5) to rapidly reduce the learning and prediction time. The network pruning algorithm is general and applicable for any classification problem.

Keywords

network pruning, minimal network structure, network demystification, weight significance, removing synapses, network pathing, feature energy, network optimization, neural network

Language used: English

Date on which the thesis was submitted / produced: 19. 5. 2017

Accessible from:: 31. 12. 2999

Thesis defence

• Supervisor: Ing. Luboš Šmídl, Ph.D.

University of West Bohemia

Faculty of Applied Sciences

Master programme / field:
Applied Sciences and Computer Engineering / Cybernetics and Control Engineering