KDnuggets Home » News » 2017 » Jun » Tutorials, Overviews » Deep Learning Zero to One: 5 Awe-Inspiring Demos with Code for Beginners ( 17:n25 )

Deep Learning Zero to One: 5 Awe-Inspiring Demos with Code for Beginners


Here are deep learning demos and examples you can just download and run. No Math. No Theory. No Books.



By Sam Putnam, Enterprise Deep Learning.

Someone in a meetup said they wanted deep learning examples that they can just download and run. No Math. No Theory. No Books.

It's difficult to find deep learning examples that are open source and that also run first try without stepping through dependency hell, so try this:

Below are 5 models I have downloaded and started running on my MacBook Pro or AWS in under 10 minutes. All ran several days to several months ago - just download and go. They finish in between 5s (pre-trained neural networks) and several hours (GPU-intensive neural network training) time. But you've got 5 seconds, right?

Please email me Sam@EnterpriseDeepLearning.com if the following doesn't work for you!
5 Awe-Inspiring Deep Learning Demos, Part1

(Editor: this is first installment of the demos - next part will be published next week).

1. Gated Conditional Pixel Convolutional Neural Network using TensorFlow



Model:


Demo:


Paper:


2. Value Iteration Networks using TensorFlow - Best Paper Award NIPS '16



Model:


Demo:

3. Flappy Bird using Deep Reinforcement Learning (Deep Q-learning)



Model:


Demo (Amazon version):

4. LSTM Music Generation with Google Magenta Basic RNN



Model:


Demo:

5. Live Captioning using Speech APIs on iOS



Model:


Demo:



Thank you to the model creators: Sash Zats, Marc Brown, Stephen Anthony, Manuel Ruder, and Shantanu Johri.

Github List:




Tutorials for demos available here: https://ai-month.teachable.com/p/the-terrible-deep-learning-list-part-1-tutorials

Author Bio: Sam Putnam is CEO/Founder, and a Deep Learning Consultant, at Enterprise Deep Learning, LLC. He directs machine learning projects, solves clients' business problems, and trains deep neural networks on large datasets. Sam is also a contributor to the TensorFlow machine learning project and a member of the Machine Learning Society.

Original. Reposted with permission.