Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications.
Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications.
复制标题
DOI：
10.3390/ijms17081313
复制
发表时间：
2016-08-11
影响因子：
5.6
通讯作者：
Porto-Pazos AB
中科院分区：
文献类型：
--
作者：
Pastur-Romay LA;Cedrón F;Pazos A;Porto-Pazos AB
在过去的十年中，深度人工神经网络（dnn）已经成为机器学习（ML）、语音识别、计算机视觉、自然语言处理和许多其他任务中最先进的算法。这得益于大数据、深度学习（DL）的进步以及芯片处理能力的大幅提高，尤其是通用图形处理单元（gpgpu）。所有这些都使人们越来越有兴趣在几乎每个领域充分利用深度神经网络的潜力。本文概述了深层神经网络的主要结构，以及它们在药理学和生物信息学中的用途。主要应用于：药物设计、虚拟筛选（VS）、定量构效关系（QSAR）研究、蛋白质结构预测和基因组学（和其他组学）数据挖掘。讨论了未来对神经形态硬件的需求，并回顾了两种最先进的芯片：IBM TrueNorth和SpiNNaker。此外，本文还指出，考虑到星形胶质细胞（一种有助于大脑信息处理的胶质细胞）的重要性，不仅要考虑神经元，因为dnn和神经形态芯片还应包括胶质细胞。深度人工神经元-星形胶质细胞网络（DANAN）可以克服当前机器学习方法在架构设计、学习过程和可扩展性方面的困难。
Over the past decade, Deep Artificial Neural Networks (DNNs) have become the state-of-the-art algorithms in Machine Learning (ML), speech recognition, computer vision, natural language processing and many other tasks. This was made possible by the advancement in Big Data, Deep Learning (DL) and drastically increased chip processing abilities, especially general-purpose graphical processing units (GPGPUs). All this has created a growing interest in making the most of the potential offered by DNNs in almost every field. An overview of the main architectures of DNNs, and their usefulness in Pharmacology and Bioinformatics are presented in this work. The featured applications are: drug design, virtual screening (VS), Quantitative Structure–Activity Relationship (QSAR) research, protein structure prediction and genomics (and other omics) data mining. The future need of neuromorphic hardware for DNNs is also discussed, and the two most advanced chips are reviewed: IBM TrueNorth and SpiNNaker. In addition, this review points out the importance of considering not only neurons, as DNNs and neuromorphic chips should also include glial cells, given the proven importance of astrocytes, a type of glial cell which contributes to information processing in the brain. The Deep Artificial Neuron–Astrocyte Networks (DANAN) could overcome the difficulties in architecture design, learning process and scalability of the current ML methods.
登录
查看更多内容
影响因子：
--
作者：
Alvarellos-González A;Pazos A;Porto-Pazos AB
通讯作者：
Porto-Pazos AB
DOI：
10.1109/tcad.2015.2474396
发表时间：
2015-10-01
影响因子：
2.9
作者：
Akopyan, Filipp;Sawada, Jun;Modha, Dharmendra S.
通讯作者：
Modha, Dharmendra S.
影响因子：
46.9
作者：
Alipanahi, Babak;Delong, Andrew;Frey, Brendan J.
通讯作者：
Frey, Brendan J.
影响因子：
4.2
作者：
Achour, S. Ben;Pascual, O.
通讯作者：
Pascual, O.