Learning Competition and Cooperation

1993 ◽  
Vol 5 (2) ◽  
pp. 242-259 ◽  
Author(s):  
Sungzoon Cho ◽  
James A. Reggia
Keyword(s):  
Learning Rule ◽  
Connection Strength ◽  
Context Sensitive ◽  
Competition And Cooperation ◽  
Activation Mechanisms ◽  
Exclusive Or ◽  
Functional Mechanisms ◽  
Inhibitory Interactions ◽  
Competitive Activation ◽  
Or Task

Competitive activation mechanisms introduce competitive or inhibitory interactions between units through functional mechanisms instead of inhibitory connections. A unit receives input from another unit proportional to its own activation as well as to that of the sending unit and the connection strength between the two. This, plus the finite output from any unit, induces competition among units that receive activation from the same unit. Here we present a backpropagation learning rule for use with competitive activation mechanisms and show empirically how this learning rule successfully trains networks to perform an exclusive-OR task and a diagnosis task. In particular, networks trained by this learning rule are found to outperform standard backpropagation networks with novel patterns in the diagnosis problem. The ability of competitive networks to bring about context-sensitive competition and cooperation among a set of units proved to be crucial in diagnosing multiple disorders.

LEARNING ACTIVATION RULES RATHER THAN CONNECTION WEIGHTS

1996 ◽  
Vol 07 (02) ◽  
pp. 129-147 ◽  
Author(s):  
ERIC L. GRUNDSTROM ◽  
JAMES A. REGGIA
Keyword(s):  
Gradient Descent ◽  
A Priori ◽  
Learning Rule ◽  
Rule Based ◽  
Activation Mechanisms ◽  
Activation Rule ◽  
Associative Recall ◽  
Selection Of ◽  
Competitive Activation ◽  
Standard Learning

In the construction of neural networks involving associative recall, information is sometimes best encoded with a local representation. Moreover, a priori knowledge can lead to a natural selection of connection weights for these networks. With predetermined and fixed weights, standard learning algorithms that work by altering connection strengths are unable to train such networks. To address this problem, this paper derives a supervised learning rule based on gradient descent, where connection weights are fixed and a network is trained by changing the activation rule. It incorporates both traditional and competitive activation mechanisms, the latter being an efficient method for instilling competition in a network. The learning rule has been implemented, and the results from several test networks demonstrate that it works effectively.

The fast–same effect of an exclusive-OR task.

2020 ◽  
Vol 46 (9) ◽  
pp. 991-1000 ◽  
Author(s):  
Marc-André Goulet ◽  
Denis Cousineau
Keyword(s):  
Exclusive Or ◽  
Or Task

Self-Lubricating PVD Hard Coatings through Tribological Activation

2020 ◽  
Vol 404 ◽  
pp. 109-116
Author(s):  
Kirsten Bobzin ◽  
Tobias Brögelmann ◽  
Nathan Christopher Kruppe ◽  
Nina Stachowski
Keyword(s):  
Physical Vapor Deposition ◽  
Layer Structure ◽  
Transition Metal Dichalcogenides ◽  
Solid Lubricants ◽  
Hard Coatings ◽  
Activation Mechanisms ◽  
Metal Dichalcogenides ◽  
State Of Research ◽  
Manufacturing Technologies ◽  
Functional Mechanisms

PVD (physical vapor deposition) hard coatings are widely used and common in manufacturing technologies, for the use as wear and oxidation protection of tools and components. Therefore, many specialized hard coatings systems have been developed until now. Nevertheless, there is a demand to improve the functionality of PVD hard coatings, i.e. due to a self-lubricating effect through tribological activation. According to the current state of research, solid lubricants with lattice layer structure and oxidic solid lubricants are particularly suitable for this purpose. This work gives an overview on the functional mechanisms as well as required environmental conditions and activation mechanisms of transition metal dichalcogenides (TMD) and Magnéli-phases.

scholarly journals A HETEROSYNAPTIC LEARNING RULE FOR NEURAL NETWORKS

2006 ◽  
Vol 17 (10) ◽  
pp. 1501-1520 ◽  
Author(s):  
FRANK EMMERT-STREIB
Keyword(s):  
Neural Networks ◽  
Learning Rule ◽  
Complex Form ◽  
Postsynaptic Neuron ◽  
Stochastic Learning ◽  
Feed Forward Network ◽  
The Mean ◽  
Efficient Learning ◽  
Exclusive Or ◽  
Selection Of

In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.

Tubulin structure at intermediate resolution

1995 ◽  
Vol 53 ◽  
pp. 852-853
Author(s):  
K. H. Downing ◽  
S. G. Wolf ◽  
E. Nogales
Keyword(s):  
High Resolution ◽  
Structural Data ◽  
Therapeutic Drug ◽  
Zinc Ions ◽  
Two Dimensional ◽  
X Ray Diffraction ◽  
X Ray ◽  
Negative Stain ◽  
Functional Mechanisms ◽  
Tubulin Structure

Microtubules are involved in a host of critical cell activities, many of which involve transport of organelles through the cell. Different sets of microtubules appear to form during the cell cycle for different functions. Knowledge of the structure of tubulin will be necessary in order to understand the various functional mechanisms of microtubule assemble, disassembly, and interaction with other molecules, but tubulin has so far resisted crystallization for x-ray diffraction studies. Fortuitously, in the presence of zinc ions, tubulin also forms two-dimensional, crystalline sheets that are ideally suited for study by electron microscopy. We have refined procedures for forming the sheets and preparing them for EM, and have been able to obtain high-resolution structural data that sheds light on the formation and stabilization of microtubules, and even the interaction with a therapeutic drug.Tubulin sheets had been extensively studied in negative stain, demonstrating that the same protofilament structure was formed in the sheets and microtubules. For high resolution studies, we have found that the sheets embedded in either glucose or tannin diffract to around 3 Å.

Neuropsychology in the Real World

2014 ◽  
Vol 25 (4) ◽  
pp. 233-238 ◽  
Author(s):  
Martin Peper ◽  
Simone N. Loeffler
Keyword(s):  
Neuropsychological Assessment ◽  
Real World ◽  
Ecological Validity ◽  
Real Life ◽  
Emotional States ◽  
Context Sensitive ◽  
Traditional Assessment ◽  
Life Data ◽  
Real Life Data ◽  
Assessment And Treatment

Current ambulatory technologies are highly relevant for neuropsychological assessment and treatment as they provide a gateway to real life data. Ambulatory assessment of cognitive complaints, skills and emotional states in natural contexts provides information that has a greater ecological validity than traditional assessment approaches. This issue presents an overview of current technological and methodological innovations, opportunities, problems and limitations of these methods designed for the context-sensitive measurement of cognitive, emotional and behavioral function. The usefulness of selected ambulatory approaches is demonstrated and their relevance for an ecologically valid neuropsychology is highlighted.

Sign in / Sign up

Export Citation Format

Share Document