Joint Training of Deep Boltzmann Machines

We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.

• Publication year

  2012

• Venue

  arXiv.org

• Publication date

  2012-12-12

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1212.2686
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Layer-wise learning of deep generative models

  2012cited by this paper
• Improving neural networks by preventing co-adaptation of feature detectors

  2012influential reference
• Learning Feature Hierarchies with Centered Deep Boltzmann Machines

  2012cited by this paper
• Empirical Risk Minimization of Graphical Model Parameters Given Approximate Inference, Decoding, and Model Structure

  2011cited by this paper
• Deep Boltzmann Machines

  2009influential reference
• Training restricted Boltzmann machines using approximations to the likelihood gradient

  2008cited by this paper
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates

  1999cited by this paper

• Machine learning and its impact on control systems: A review

  2021cites this paper
• Neural Network Imitation Model of Realization of the Business Analysis Process

  2021cites this paper
• Integrating long-range regulatory interactions to predict gene expression using graph convolutional neural networks

  2020cites this paper
• Minimax formula for the replica symmetric free energy of deep restricted Boltzmann machines

  2020cites this paper
• Classification of User Movement Data

  2018cites this paper
• Recognition of asphalt pavement crack length using deep convolutional neural networks

  2018cites this paper
• Component Pin Recognition Using Algorithms Based on Machine Learning

  2018cites this paper
• Towards Scalable Parallel Training of Deep Neural Networks

  2017cites this paper
• DeepFlow: a deep learning framework for software-defined measurement

  2017cites this paper
• Practical Secure Aggregation for Privacy-Preserving Machine Learning

  2017cites this paper
• Machine Learning--Based Parametric Audiovisual Quality Prediction Models for Real-Time Communications

  2017cites this paper
• Deep learning challenges and solutions with Xilinx FPGAs

  2017cites this paper
• A comparative study of deep learning models for medical image classification

  2017cites this paper
• Ask the GRU: Multi-task Learning for Deep Text Recommendations

  2016cites this paper
• Evolutionary generation of adversarial examples for deep and shallow machine learning models

  2016cites this paper
• DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks

  2016cites this paper
• Bin Picking Using Manifold Learning

  2016cites this paper
• Modeling Joint Representation with Tri-Modal Deep Belief Networks for Query and Question Matching

  2016cites this paper
• Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM

  2016cites this paper
• 3D object understanding with 3D Convolutional Neural Networks

  2016cites this paper
• Training Deep Nets with Sublinear Memory Cost

  2016cites this paper
• Document Modeling with Gated Recurrent Neural Network for Sentiment Classification

  2015cites this paper
• Generating News Headlines with Recurrent Neural Networks

  2015cites this paper
• Using Financial Reports to Predict Stock Market Trends With Machine Learning Techniques

  2015cites this paper
• 3D object retrieval with stacked local convolutional autoencoder

  2015cites this paper
• Maxout Networks

  2013cites this paper
• Deep Learning of Representations: Looking Forward

  2013cites this paper