Python‎ > ‎

How to implement a neural network in Python

posted Jun 12, 2015, 9:09 AM by Chris G   [ updated Jan 11, 2016, 11:05 AM ]
A Python great tutorial:


Using neural nets to recognize handwritten digits





How the backpropagation algorithm works





Brain-inspired algorithms may make for optimized computational networks






Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs







NVIDIA Get Started with Deep Learning



  • If you are a data scientist designing neural networks for image classification use the NVIDIA Deep Learning GPU Training System (DIGITS)
  • If you are a deep learning researcher or developer choose one of these widely-used open source deep learning frameworks and accelerate it with the CUDA Deep Neural Network (cuDNN) library:
    • Caffe – developed by Yangqing Jia while in the PhD program at University of California at Berkeley
    • Theano - A Python library that allows you to efficiently define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays
    • Torch - A scientific computing framework with wide support for machine learning algorithms

  • Andrew Ng's Coursera course provides a good introduction to deep learning (Coursera, YouTube)
  • Yann LeCun’s NYU Course on Deep Learning, Spring 2014 (TechTalks)
  • Geoffrey Hinton's “Neural Networks for Machine Learning” course from Oct 2012 (Coursera)
  • Rob Fergus's "Deep Learning for Computer Vision" tutorial from NIPS 2013 (slides, video)
  • Caltech's introductory deep learning course taught by Yasser Abu-Mostafa (YouTube)
  • Stanford CS224d: Deep Learning for Natural Language Processing (video, slides, tutorials)