Passive Dendrites Enable Single Neurons to Compute Linearly Non-separable Functions
نویسندگان
چکیده
منابع مشابه
Passive Dendrites Enable Single Neurons to Compute Linearly Non-separable Functions
Local supra-linear summation of excitatory inputs occurring in pyramidal cell dendrites, the so-called dendritic spikes, results in independent spiking dendritic sub-units, which turn pyramidal neurons into two-layer neural networks capable of computing linearly non-separable functions, such as the exclusive OR. Other neuron classes, such as interneurons, may possess only a few independent dend...
متن کاملNon - Separable Cryptographic Functions
We study nonlinear Boolean functions that are used in cryptography, especially in block and stream ciphers. We point out possible cryptographic weaknesses of the so-called separable functions. A characteristic of these functions is that they can be transformed into ones that are composed of two “sub-functions” with disjoint variables. We then proceed to construct non-separable functions that ex...
متن کاملLinearly Separable Boolean Function
The maximum absolute value of integral weights sufficient to represent any linearly separable Boolean function is investigated. It is shown that upper bounds exhibited by Muroga (1971) for rational weights satisfying the normalized System of inequalities also hold for integral weights. Therewith, the previous best known upper bound for integers is improved by approximately a factor of 1/2.
متن کاملLearning Linearly Separable Languages
For a finite alphabet A, we define a class of embeddings of A∗ into an infinite-dimensional feature space X and show that its finitely supported hyperplanes define regular languages. This suggests a general strategy for learning regular languages from positive and negative examples. We apply this strategy to the piecewise testable languages, presenting an embedding under which these are precise...
متن کاملLearning Non-Linearly Separable Boolean Functions With Linear Threshold Unit Trees and Madaline-Style Networks
This paper investigates an algorithm for the construction of decisions trees comprised of linear threshold units and also presents a novel algorithm for the learning of nonlinearly separable boolean functions using Madalinestyle networks which are isomorphic to decision trees. The construction of such networks is discussed, and their performance in learning is compared with standard BackPropaga...
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: PLoS Computational Biology
سال: 2013
ISSN: 1553-7358
DOI: 10.1371/journal.pcbi.1002867