Tools
- PyBrain – neural network library in Python
- Theano – a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.
- scikit-learn – it has some useful dataset generators, so we don’t need to write the code ourselves.
- nolearn – deep learning packages for Python
- lasagne
- caffe
- kera
- GloVe – Global Vectors for Word Representation
Resources
- Deep Learning – show you how to use nolearn and sklearn to build your first neural net with handwriting recognition (minst dataset).
- Deep Learning on GPU
- Build your first image search engine and its pdf
- A fast learning algorithm for deep belief nets – paper in pdf
- Morvan’s github examples
- PyImageSearch Computer Vision Course Syllabus
- Visual Logging
- Optimizing Gradient Descent
- Stochastic Gradient Descent vs Gradient Descent – SGD is about 1 training data point at each step while GD will need to go thru all traning dataset for each step.
- Use cross entropy error
- Understanding convolutional neural networks (CNN) for NLP
- CNN for text classification
- RNN for Text
- Word Embedding
- Great Explanation of Word Embedding
- Word Embedding Explained
- Softmax and Cross-Entropy and stanford and Great Explanation
- Deep Learning Lecture
Connect with us