James Martens

Publications by Year

Research Areas

Stochastic Gradient Optimization Techniques, Neural Networks and Applications, Advanced Neural Network Applications, Model Reduction and Neural Networks, Domain Adaptation and Few-Shot Learning

Most-Cited Works

• On the importance of initialization and momentum in deep learning(2013)
• Generating Text with Recurrent Neural Networks(2011)
• Deep learning via Hessian-free optimization(2010)
• Learning Recurrent Neural Networks with Hessian-Free Optimization(2011)
• → Optimizing Neural Networks with Kronecker-factored Approximate Curvature(2015)290 cited
• → Adding Gradient Noise Improves Learning for Very Deep Networks(2015)265 cited
• New Insights and Perspectives on the Natural Gradient Method(2020)
• → Training Deep and Recurrent Networks with Hessian-Free Optimization(2012)205 cited
• Adversarial Robustness through Local Linearization(2019)