The importance of data for training intelligent devices
A Esposito - From Synapses to Rules: Discovering Symbolic Rules …, 2002 - Springer
In the past decade there has been a big effort in implementing automatic systems that can
be used in most environments and are able to decrease human work and therefore, human …
be used in most environments and are able to decrease human work and therefore, human …
Why Neural Computing?
I Aleksander - Journal of Information Technology, 1989 - journals.sagepub.com
The sudden growth of interest in neural computing is a remarkable phenomenon that will be
seen by future historians ofcomputer science as marking the 1980s in much the same way …
seen by future historians ofcomputer science as marking the 1980s in much the same way …
On the need for a neural abstract machine
D Sona, A Sperduti - Sequence Learning: Paradigms, Algorithms, and …, 2001 - Springer
The complexity of learning tasks and their variety, as well as the number of different neural
networks models for sequence learning is quite high. Moreover, in addition to architectural …
networks models for sequence learning is quite high. Moreover, in addition to architectural …
Challenges in neural computation
B Hammer - KI-Künstliche Intelligenz, 2012 - Springer
Challenges in Neural Computation | SpringerLink Skip to main content Advertisement
SpringerLink Log in Menu Find a journal Publish with us Search Cart 1.Home 2.KI - Künstliche …
SpringerLink Log in Menu Find a journal Publish with us Search Cart 1.Home 2.KI - Künstliche …
A general framework for learning rules from data
With the aim of getting understandable symbolic rules to explain a given phenomenon, we
split the task of learning these rules from sensory data in two phases: a multilayer perceptron …
split the task of learning these rules from sensory data in two phases: a multilayer perceptron …
[图书][B] From synapses to rules: discovering symbolic rules from neural processed data
B Apolloni, F Kurfess - 2012 - books.google.com
One high-level ability of the human brain is to understand what it has learned. This seems to
be the crucial advantage in comparison to the brain activity of other primates. At present we …
be the crucial advantage in comparison to the brain activity of other primates. At present we …
Extracting DNF rules from artificial neural networks
Artificial neural networks are powerful classification mechanisms. Neural networks encode
knowledge in a set of numerical weights and biases. This data driven aspect of neural …
knowledge in a set of numerical weights and biases. This data driven aspect of neural …
Stuttgart Neural Network Simulator: Exploring connectionism and machine learning with SNNS
E Petron - Linux Journal, 1999 - dl.acm.org
Conventional algorithmic solution methods require the application of unambiguous
definitions and procedures. This requirement makes them impractical or unsuitable for …
definitions and procedures. This requirement makes them impractical or unsuitable for …
[PDF][PDF] Neural networks and artificial intelligence
S Kak - Information sciences, 1993 - academia.edu
Neural structures that constitute the brain outperform the most powerful computers at tasks
that are generally described as requiring intelligence. These are the tasks involving …
that are generally described as requiring intelligence. These are the tasks involving …