Index of papers in PLOS Comp. Biol. that mention
  • learning algorithms
Kai Olav Ellefsen, Jean-Baptiste Mouret, Jeff Clune
Abstract
That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills.
Background
The problem occurs because learning algorithms only focus on solving the current problem and change any connections that will help solve that problem, even if those connections encoded skills appropriate to previously encountered problems [9].
Background
Novelty vectors modify the backpropagation learning algorithm [7] to limit the number of connections that are changed in the network based on how novel, or unexpected, the input pattern is [29].
Background
Another approach to determining the weights of neural networks is to initialize them randomly and then allow them to change via a learning algorithm [5, 7, 45].
Introduction
To learn new skills, neural network learning algorithms change the weights of neural connections [6—8], but old skills are lost because the weights that encoded old skills are changed to improve performance on new tasks.
learning algorithms is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Sébastien Giguère, François Laviolette, Mario Marchand, Denise Tremblay, Sylvain Moineau, Xinxia Liang, Éric Biron, Jacques Corbeil
Improving the bioactivity of peptides
It is common for machine learning algorithms to sacrifice accuracy on the training data to prevent overfitting.
Improving the bioactivity of peptides
Another possible explanation for this discrepancy is that the biological activity of VEWAK could be slightly erroneous as the learning algorithm could not find a simple model given such an outlier.
Improving the bioactivity of peptides
Hence, our proposed learning algorithm predicts new peptides having biological activities equivalent to the best of the training set and, in some cases, substantially improved activities.
Introduction
By incorporating valuable biological and chemical knowledge, kernels provide an efficient way to improve the accuracy of learning algorithms .
Introduction
This work explores the use of learning algorithms to design and enhance the pharmaceutical properties of compounds [12, 13].
The machine learning approach
The proposed solution for drug design is thus compatible with these popular bioinformatics learning algorithms [21].
The machine learning approach
Since a PSWM assumes statistical independence between positions in the pattern, the probability that a sequence belongs to a certain pattern is given by summing the corresponding entries in M. PSWM are simple but have, however, been surpassed by modern machine learning algorithms [22, 23] since they assume independence between positions in the pattern.
learning algorithms is mentioned in 7 sentences in this paper.
Topics mentioned in this paper:
Naoki Hiratani, Tomoki Fukai
Abstract
To explore the answers to these questions, we construct models of feedforward networks with lateral inhibitory circuits and study how propagated correlation influences STDP learning, and what kind of learning algorithm such circuits achieve.
Author Summary
Our results also suggest that neural circuits make use of stochastic membrane dynamics to approximate computationally compleX Bayesian learning algorithms , progressing our understanding of the principles of stochastic computation by the brain.
Introduction
We further found a possible link between stochastic membrane dynamics and sampling process, which is necessary for neural approximation of learning algorithm of Bayesian independent component analysis (ICA).
pf = 1 — <1 — rsAofi [1 — am: ask/szy] ,qsk = 2; 3 M + 1/2>At12exp[—<k + mam/at].
Although the performance of STDP is much worse than the ideal case (when the true Q is given), this performance is similar to that for the sample-based learning algorithm discussed above (Fig 7C).
learning algorithms is mentioned in 4 sentences in this paper.
Topics mentioned in this paper: