Reducing computational costs in deep learning on almost linearly separable training data
نویسندگان
چکیده
منابع مشابه
Learning 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 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 کاملAlmost Separable Matrices
An m × n matrix A with column supports {Si} is k-separable if the disjunctions ⋃ i∈K Si are all distinct over all sets K of cardinality k. While a simple counting bound shows that m > k log2 n/k rows are required for a separable matrix to exist, in fact it is necessary for m to be about a factor of k more than this. In this paper, we consider a weaker definition of ‘almost k-separability’, whic...
متن کاملComputational biology: deep learning
Deep learning is the trendiest tool in a computational biologist’s toolbox. This exciting class of methods, based on artificial neural networks, quickly became popular due to its competitive performance in prediction problems. In pioneering early work, applying simple network architectures to abundant data already provided gains over traditional counterparts in functional genomics, image analys...
متن کاملAlmost Separable Data Aggregation by Layers of Formal Neurons1
Information extraction or knowledge discovery from large data sets should be linked to data aggregation process. Data aggregation process can result in a new data representation with decreased number of objects of a given set. A deterministic approach to separable data aggregation means a lesser number of objects without mixing of objects from different categories. A statistical approach is les...
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: Computer Optics
سال: 2020
ISSN: 2412-6179,0134-2452
DOI: 10.18287/2412-6179-co-645