Subscribe to DSC Newsletter

An Old Problem - Ep. 5 (Deep Learning SIMPLIFIED)

While Deep Neural Nets are the state of the art in machine learning, the flipside is that they are really hard to train. Up until 2006, there was no way to train them satisfactorily. Here is a clip that explains further.

If deep neural networks are so powerful, why aren’t they used more often? The reason is that they are very difficult to train due to an issue known as the va...

Views: 198

Get Embed Code

Tags: AI, Artificial Intelligence, Backpropagation, CUDA, Classification, More…Convolutional Neural Network, Deep Belief Network, Deep Learning, Deep Neural Networks, GPU, Gradient Descent, Image Compression, Image recognition, LSTM, Machine Learning, Multilayer Perceptron, Neural Network, OCR, Optical Character Recognition, Pattern Recognition, Recurrent Neural Network, SVM, Stock Market Prediction, Support Vector Machine, Theano, indico, nvidia

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Resources

Videos

  • Add Videos
  • View All

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service