- Data Science 101: Preventing Overfitting in Neural Networks - Apr 17, 2015.
Overfitting is a major problem for Predictive Analytics and especially for Neural Networks. Here is an overview of key methods to avoid overfitting, including regularization (L2 and L1), Max norm constraints and Dropout.
Pages: 1 2
Neural Networks, Nikhil Buduma, Overfitting, Regularization
- Deep Learning, The Curse of Dimensionality, and Autoencoders - Mar 12, 2015.
Autoencoders are an extremely exciting new approach to unsupervised learning and for many machine learning tasks they have already surpassed the decades of progress made by researchers handpicking features.
Pages: 1 2 3
Autoencoder, Deep Learning, Face Recognition, Geoff Hinton, Image Recognition, Nikhil Buduma
- Deep Learning in a Nutshell – what it is, how it works, why care? - Jan 12, 2015.
Deep learning and neural networks are increasingly important concepts in computer science with great strides being made by large companies like Google and startups like DeepMind.
Brain, Deep Learning, DeepMind, Neural Networks, Nikhil Buduma
