Invited lecture of ICONIP 2017
Deep Learning and a New Approach for Machine Learning
A basis of AI is machine learning, whose state of the art is mainly the highly publicized deep learning. Due to its unique features, deep learning seems irreplaceable in some applications. However, its development for other applications especially cognitive computing has been stagnant. In this talk, some fundamental shortcomings of deep learning will be examined in connection with big data.
A postulational approach based on 4 biological and 1 creationist/evolutionary postulates has yielded a computational model of biological neural networks and a cortex-like learning machine. The former has a logically coherent explanation of how the brain encodes, learns, memorizes, recalls and generalizes. The latter has avoided the fundamental shortcomings of deep learning. The new model and machine will briefly be introduced in the talk.
- Paper Submission Deadline
June 15, 2017
June 30, 2017 - Notification of Acceptance
July 31, 2017 - Final Paper Submission
August 20, 2017 - Congress Date
November 14–18, 2017
Contact Us
Address: 95 Zhongguancun East Road,
Beijing 100190, China
Email: iconip2017@foxmail.com
Fax: +86-10-8254-4799