Neural networks, manifolds, and topology

Click for: original source

Christopher Olah older article about excitement and interest in deep neural networks because they’ve achieved breakthrough results in areas such as computer vision.

However, there remain a number of concerns about them. One is that it can be quite challenging to understand what a neural network is really doing. It is much easier to explore low-dimensional deep neural networks – networks that only have a few neurons in each layer.

Author then provides more information on:

  • Simple neural network example
  • Continuous visualization of layers
  • Topology of tanh layers
  • Topology and Classification
  • The Manifold Hypothesis

Excellent article with still relevant information for anybody interested in neural networks.

[Read More]

Tags big-data machine-learning