Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published August 19, 2019 | Version v1
Conference paper Open

Artificial Neural Networks: the missing link between curiosity and accuracy

  • 1. University of Modena and Reggio Emilia

Description

Artificial Neural Networks, as the name itself suggests, are biologically inspired algorithms designed to simulate the way in which the human brain processes information. Like neurons, which consist of a cell nucleus that receives input from other neurons through a web of input terminals, an Artificial Neural Network includes hundreds of single units, artificial neurons or processing elements, connected with coefficients (weights), and are organized in layers. The power of neural computations comes from connecting neurons in a network: in fact, in an Artificial Neural Network it is possible to manage a different number of information at the same time. What is not fully understood is which is the most efficient way to train an Artificial Neural Network, and in particular what is the best mini-batch size for maximize accuracy while minimizing training time. The idea that will be developed in this study has its roots in the biological world, that inspired the creation of Artifi- cial Neural Network in the first place.

Humans have altered the face of the world through extraordinary adap- tive and technological advances: those changes were made possible by our cognitive structure, particularly the ability to reasoning and build causal models of external events. This dynamism is made possible by a high degree of curiosity. In the biological world, and especially in human beings, curiosity arises from the constant search of knowledge and infor- mation: behaviours that support the information sampling mechanism range from the very small (initial mini-batch size) to the very elaborate sustained (increasing mini-batch size).

The goal of this project is to train an Artificial Neural Network by in- creasing dynamically, in an adaptive manner (with validation set), the mini-batch size; our hypothesis is that this training method will be more efficient (in terms of time and costs) compared to the ones implemented so far.

Files

ANN.pdf

Files (683.1 kB)

Name Size Download all
md5:4e61e3d392347e26b7ec377fa3443128
683.1 kB Preview Download

Additional details

Funding

CLASS – Edge and CLoud Computation: A Highly Distributed Software Architecture for Big Data AnalyticS 780622
European Commission