Northwestern University

Parent Unit Name

Login

LIBRARIES | ARCH

Menu Search

Start Over

Filtering by: Keyword Activation Functions Keyword Machine Learning Keyword Stock Prediction Resource type Dissertation

1 entry found

List Gallery Masonry Slideshow

Q524jp00q?file=thumbnail

1. Methods for Images, Time Series, and Activation Functions with Deep Neural Networks

Description:: In this work, we explore the utility of the three main types of neural networks: feed forward, convolutional, and recurrent. While using these networks, we develop a new way to model multiagent trajectory data, explore the use of multiple activation functions for neurons at each layer of a neural network,...
Keyword:: Stock Prediction, Deep Learning, Basketball Trajectory, Activation Functions, and Machine Learning
Subject:: Engineering Sciences and Applied Mathematics
Creator:: Mark Harmon
Owner:: Scholarly Digital Publishing
Date Uploaded:: 10/14/2019
Date Modified:: 10/14/2019
Date Created:: 2018-01-01
Resource Type:: Dissertation