GitHub - marcotav/deep-learning: Projects include the application of transfer learning to build a convolutional neural network (CNN) that identifies the artist of a painting, the building of predictive models for Bitcoin price data using Long Short-Term Memory recurrent neural networks (LSTMs) and a tutorial explaining how to build two types of neural network using as input the MNIST dataset, namely, a CNN using Keras and a fully-connected network using TensorFlow.

Deep Learning Projects

Project	Brief Description
painter-identifier	I built a Convolutional Neural Net to identify the artist of a painting via transfer learning, instantiating the convolutional part of the Inception V3 model, and training a fully-connected network on top.
bitcoin-price-analysis	I built predictive models for Bitcoin price data using recurrent neural networks (LSTMs). Correlations between altcoins are also considered.
keras-tf-tutorial	Neural networks tutorial where I build fully-connected networks and convolutional neural networks using both Keras and TensorFlow respectively (in progress).
transfer-learning-mini-tutorial	I illustrate the use of transfer learning using the Inception V3 deep neural network model.

Feel free to contact me:

Name		Name	Last commit message	Last commit date
Latest commit History 173 Commits
all-scripts		all-scripts
bitcoin		bitcoin
image-recognition-tutorial		image-recognition-tutorial
images		images
keras-tf-tutorial		keras-tf-tutorial
painters-identification		painters-identification
transfer-learning		transfer-learning
README.md		README.md
bitcoin.py		bitcoin.py
painters.py		painters.py
transfer-learning.py		transfer-learning.py