Activity Number:
|
253
- Contributed Poster Presentations: Quantum Computing in Statistics and Machine Learning
|
Type:
|
Contributed
|
Date/Time:
|
Monday, July 29, 2019 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Quantum Computing in Statistics and Machine Learning
|
Abstract #306421
|
|
Title:
|
Optimization of Backpropagation Multilayer Neural Network
|
Author(s):
|
Jun Kim* and Anindya Bhadra
|
Companies:
|
Purdue University and Purdue University
|
Keywords:
|
Machine Learning;
Neural Network
|
Abstract:
|
While there has been a growing interest of optimization implements into a neural network, one known method are mini-batches. While batch gradient descent may result in a more stable convergence on some problems, it can also result in a premature convergence of a model. A mini-batch gradient descent allows a more robust convergence, which may allow the neural network to avoid local minima. This poster will explore the optimum number of mini-batch sizes on different sizes of data set by using a gradient descent multilayer backpropagation model.
|
Authors who are presenting talks have a * after their name.