27
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: not found
      • Article: not found

      Designing neural networks through neuroevolution

      , , ,
      Nature Machine Intelligence
      Springer Nature

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Related collections

          Most cited references66

          • Record: found
          • Abstract: not found
          • Book Chapter: not found

          Identity Mappings in Deep Residual Networks

            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Deep Learning in Neural Networks: An Overview

            (2014)
            In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              LSTM: A Search Space Odyssey

              Several variants of the long short-term memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful functional ANalysis Of VAriance framework. In total, we summarize the results of 5400 experimental runs ( ≈ 15 years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
                Bookmark

                Author and article information

                Journal
                Nature Machine Intelligence
                Nat Mach Intell
                Springer Nature
                2522-5839
                January 2019
                January 7 2019
                January 2019
                : 1
                : 1
                : 24-35
                Article
                10.1038/s42256-018-0006-z
                83fbb6b2-c647-4211-bb96-dd4ad636c4c3
                © 2019

                http://www.springer.com/tdm

                History

                Comments

                Comment on this article