The Experts below are selected from a list of 255 Experts worldwide ranked by ideXlab platform

Jun S Song - One of the best experts on this subject based on the ideXlab platform.

  • Maximum Entropy Methods for extracting the learned features of deep neural networks
    PLOS Computational Biology, 2017
    Co-Authors: Alex I Finnegan, Jun S Song
    Abstract:

    New architectures of multilayer artificial neural networks and new Methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the Maximum Entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the Maximum Entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

  • Maximum Entropy Methods for extracting the learned features of deep neural networks
    bioRxiv, 2017
    Co-Authors: Alex I Finnegan, Jun S Song
    Abstract:

    New architectures of multilayer artificial neural networks and new Methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the Maximum Entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the Maximum Entropy distribution, similar to the grand canonical ensemble in statistical physics, also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Scf Chan - One of the best experts on this subject based on the ideXlab platform.

  • Sentiment Analysis of Product Reviews
    Encyclopedia of Data Warehousing and …, 2008
    Co-Authors: Cwk Leung, Scf Chan
    Abstract:

    Now a day's internet is the most valuable source of learning, getting ideas, reviews for a product or a service. Everyday millions of reviews are generated in the internet about a product, person or a place. Because of their huge number and size it is very difficult to handle and understand such reviews. Sentiment analysis is such a research area which understands and extracts the opinion from the given review and the analysis process includes natural language processing (NLP), computational linguistics, text analytics and classifying the polarity of the opinion. In the field of sentiment analysis there are many algorithms exist to tackle NLP problems. Each algorithm is used by several applications. In this paper we have shown the taxonomy of various sentiment analysis Methods. This paper also shows that Support vector machine (SVM) gives high accuracy compared to Naïve bayes and Maximum Entropy Methods.

Bastien Chopard - One of the best experts on this subject based on the ideXlab platform.

  • improving predictability of time series using Maximum Entropy Methods
    EPL, 2015
    Co-Authors: Gregor Chliamovitch, Alexandre Dupuis, Anton Golub, Bastien Chopard
    Abstract:

    We discuss how Maximum Entropy Methods may be applied to the reconstruction of Markov processes underlying empirical time series and compare this approach to usual frequency sampling. It is shown that, at least in low dimension, there exists a subset of the space of stochastic matrices for which the MaxEnt method is more efficient than sampling, in the sense that shorter historical samples have to be considered to reach the same accuracy. Considering short samples is of particular interest when modelling smoothly non-stationary processes, for then it provides, under some conditions, a powerful forecasting tool. The method is illustrated for a discretized empirical series of exchange rates.

Alex I Finnegan - One of the best experts on this subject based on the ideXlab platform.

  • Maximum Entropy Methods for extracting the learned features of deep neural networks
    PLOS Computational Biology, 2017
    Co-Authors: Alex I Finnegan, Jun S Song
    Abstract:

    New architectures of multilayer artificial neural networks and new Methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the Maximum Entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the Maximum Entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

  • Maximum Entropy Methods for extracting the learned features of deep neural networks
    bioRxiv, 2017
    Co-Authors: Alex I Finnegan, Jun S Song
    Abstract:

    New architectures of multilayer artificial neural networks and new Methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the Maximum Entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the Maximum Entropy distribution, similar to the grand canonical ensemble in statistical physics, also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Cwk Leung - One of the best experts on this subject based on the ideXlab platform.

  • Sentiment Analysis of Product Reviews
    Encyclopedia of Data Warehousing and …, 2008
    Co-Authors: Cwk Leung, Scf Chan
    Abstract:

    Now a day's internet is the most valuable source of learning, getting ideas, reviews for a product or a service. Everyday millions of reviews are generated in the internet about a product, person or a place. Because of their huge number and size it is very difficult to handle and understand such reviews. Sentiment analysis is such a research area which understands and extracts the opinion from the given review and the analysis process includes natural language processing (NLP), computational linguistics, text analytics and classifying the polarity of the opinion. In the field of sentiment analysis there are many algorithms exist to tackle NLP problems. Each algorithm is used by several applications. In this paper we have shown the taxonomy of various sentiment analysis Methods. This paper also shows that Support vector machine (SVM) gives high accuracy compared to Naïve bayes and Maximum Entropy Methods.