"Most influential data science research papers for 2018." "A new backpropagation algorithm without gradient...
Originally shared by Wayne Radinsky
"Most influential data science research papers for 2018." "A new backpropagation algorithm without gradient descent", "Deep learning for sentiment analysis: a survey", "Deep learning: an introduction for applied mathematicians", "On the origin of deep learning", "Recent advances in recurrent neural networks", "Deep learning: a critical appraisal", "The matrix calculus you need for deep learning", "Group normalization", "Averaging weights leads to wider optima and better generalization", "A survey on neural network-based summarization methods", "Neural style transfer: a review", "geomstats: a Python package for Riemannian geometry in machine learning", "A more general robust loss function", "Backdrop: stochastic backpropagation", "Relational deep reinforcement learning", "An intriguing failing of convolutional neural networks and the CoordConv solution", "Backprop evolution", "Recent advances in object detection in the age of deep convolutional neural networks", "Neural approaches to conversational AI", and "Reversible recurrent neural networks".
https://opendatascience.com/most-influential-data-science-research-papers-for-2018/
"Most influential data science research papers for 2018." "A new backpropagation algorithm without gradient descent", "Deep learning for sentiment analysis: a survey", "Deep learning: an introduction for applied mathematicians", "On the origin of deep learning", "Recent advances in recurrent neural networks", "Deep learning: a critical appraisal", "The matrix calculus you need for deep learning", "Group normalization", "Averaging weights leads to wider optima and better generalization", "A survey on neural network-based summarization methods", "Neural style transfer: a review", "geomstats: a Python package for Riemannian geometry in machine learning", "A more general robust loss function", "Backdrop: stochastic backpropagation", "Relational deep reinforcement learning", "An intriguing failing of convolutional neural networks and the CoordConv solution", "Backprop evolution", "Recent advances in object detection in the age of deep convolutional neural networks", "Neural approaches to conversational AI", and "Reversible recurrent neural networks".
https://opendatascience.com/most-influential-data-science-research-papers-for-2018/
Comments
Post a Comment