scholarly journals Comparison of Artificial Intelligence and Human Motivation

2021 ◽  
Vol 25 ◽  
pp. 345-351
Author(s):  
Seoyeon Yoo
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
The Other ◽  
Neural Network Learning ◽  
Internal Process ◽  
Human Motivation ◽  
Network Learning ◽  
The Past ◽  
New Ideas ◽  
To Come

According to Maslow's hierarchy of needs, humans act according to their needs. Humans also act with an interest in the internal process itself, rather than solely based on external rewards. Artificial intelligence, on the other hand, is trained through a large amount of data and neural network learning. Unlike humans who are greatly affected by emotions and various circumstances, AI is neutral and objective. With no clear limitations and vast potential for development. AI has been receiving a lot of attention. Many futurists say AI will replace humans in areas that we, in the past, couldn’t imagine machines doing the work. However, there are still areas where AI cannot replace humans. Metacognition to judge one's thoughts and creativity, the power to come up with new ideas, still remains in human domains that artificial intelligence has not been able to enter. This paper explores the reinforcement of humans and AI and explores the original human realm. Furthermore, understanding the original human domain can suggest developing human competitiveness.

Speed up Neural Network Learning by GPGPU

2011 ◽  
Vol 131 (11) ◽  
pp. 1889-1894
Author(s):  
Yuta Tsuchida ◽  
Michifumi Yoshioka
Keyword(s):  
Neural Network ◽  
Neural Network Learning ◽  
Network Learning ◽  
Speed Up

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

LOCALLY IMPLEMENTABLE MATRIX FLOWS AND THEIR APPLICATION TO NEURAL NETWORK LEARNING

1994 ◽  
Vol 04 (01) ◽  
pp. 23-51 ◽  
Author(s):  
JEROEN DEHAENE ◽  
JOOS VANDEWALLE
Keyword(s):  
Neural Network ◽  
Signal Processing ◽  
Network Structure ◽  
Adaptive Signal Processing ◽  
External Signal ◽  
Neural Network Learning ◽  
Network Learning ◽  
Adaptive Signal

A number of matrix flows, based on isospectral and isodirectional flows, is studied and modified for the purpose of local implementability on a network structure. The flows converge to matrices with a predefined spectrum and eigenvectors which are determined by an external signal. The flows can be useful for adaptive signal processing applications and are applied to neural network learning.

Sign in / Sign up

Export Citation Format

Share Document