A Biologically Supported Error-Correcting Learning Rule
نویسندگان
چکیده
منابع مشابه
A Biologically Supported Error-Correcting Learning Rule
We show that a form of synaptic plasticity recently discovered in slices of the rat visual cortex (Artola et al. 1990) can support an error-correcting learning rule. The rule increases weights when both preand postsynaptic units are highly active, and decreases them when pre-synaptic activity is high and postsynaptic activation is less than the threshold for weight increment but greater than a ...
متن کاملA more biologically plausible learning rule for neural networks.
Many recent studies have used artificial neural network algorithms to model how the brain might process information. However, back-propagation learning, the method that is generally used to train these networks, is distinctly "unbiological." We describe here a more biologically plausible learning rule, using reinforcement learning, which we have applied to the problem of how area 7a in the post...
متن کاملA Probabilistic Error-Correcting Scheme
In the course of research in Computational Learning Theory, we found ourselves in need of an error-correcting encoding scheme for which few bits in the codeword yield no information about the plain message. Being unaware of a previous solution, we came-up with the scheme presented here. Since this scheme may be of interest to people working in Cryptography, we thought it may be worthwhile to \p...
متن کاملEffectiveness of Error Correcting Output Codes in Multiclass Learning Problems
Classification (machine learning): How does one algorithmically classify the though a more effective approach could be using error correcting codes: @(cs/9501101) Solving Multiclass Learning Problems via Error-Correcting Output Codes. to solving machine learning problems can be broadly useful.
متن کاملSolving Multiclass Learning Problems via Error-Correcting Output Codes
Multiclass learning problems involve nding a de nition for an unknown function f(x) whose range is a discrete set containing k > 2 values (i.e., k \classes"). The de nition is acquired by studying collections of training examples of the form hxi; f(xi)i. Existing approaches to multiclass learning problems include direct application of multiclass algorithms such as the decision-tree algorithms C...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neural Computation
سال: 1991
ISSN: 0899-7667,1530-888X
DOI: 10.1162/neco.1991.3.2.201