Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd

A crash course in six episodes for software developers who want to become machine learning practitioners.
https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd

Last synced: 5 days ago
JSON representation

A crash course in six episodes for software developers who want to become machine learning practitioners.

Awesome Lists containing this project

README 

        

    

        

            
Featured code sample


            tensorflow-planespotting


            Code from the Google Cloud NEXT 2018 session "Tensorflow, deep

            learning and modern convnets, without a PhD". Other samples from the "Tensorflow without a PhD" series are in

            this repository too.

        Tensorflow, deep
<br />        learning and modern convnets, without a PhD

    







## Tensorflow and deep learning without a PhD series by [@martin_gorner](https://twitter.com/martin_gorner).



A crash course in six episodes for software developers who want to learn machine learning, with examples, theoretical concepts,

and engineering tips, tricks and best practices to build and train the neural networks that solve your problems.



    

        Tensorflow and deep learning without a PhD

        

            


                     video |

                     slides |

                     codelab |

                     code





                     
The basics of building neural networks for software engineers. Neural weights and biases, activation functions, supervised learning and gradient descent.

                     Tips and best practices for efficient training: learning rate decay, dropout regularisation and the intricacies of overfitting. Dense and convolutional neural networks. This session starts with low-level

                     Tensorflow and also has a sample of high-level Tensorflow code using layers and Datasets. Code sample: MNIST handwritten digit recognition with 99% accuracy. Duration: 55 min


    

    

        


                                          video |

                                          slides |

                                          code





                                          
What is batch normalisation, how to use it appropriately and how to see if it is working or not.

                                          Code sample: MNIST handwritten digit recognition with 99.5% accuracy. Duration: 25 min


        The superpower: batch normalization

    

    

        Tensorflow, deep learning and recurrent neural networks, without a PhD

        

            


                 video |

                 slides |

                 codelab |

                 code





                 
 RNN basics: the RNN cell as a state machine, training and unrolling (backpropagation through time).

                 More complex RNN cells: LSTM and GRU cells. Application to language modeling and generation. Tensorflow APIs for RNNs.

                 Code sample: RNN-generated Shakespeare play. Duration: 55 min


    

    

        


                  video |

                  slides |

                  code





                  
Convolutional neural network architectures for image processing. Convnet basics, convolution filters and how to stack them. 

                  Learnings from the Inception model: modules with parallel convolutions, 1x1 convolutions. A simple modern convnet architecture: Squeezenet.

                  Convenets for detection: the YOLO (You Look Only Once) architecture. Full-scale model training and serving with Tensorflow's Estimator API on Google

                  Cloud ML Engine and Cloud TPUs (Tensor Processing Units).

                  Application: airplane detection in aerial imagery. Duration: 55 min


        Tensorflow, deep learning and modern convnets, without a PhD

    

    

            Tensorflow, deep learning and modern RNN architectures, without a PhD

            

                


                     video |

                     slides |

                     code





                     
Advanced RNN architectures for natural language processing. Word embeddings, text classification,

                     bidirectional models, sequence to sequence models for translation. Attention mechanisms. This session also explores

                     Tensorflow's powerful seq2seq API. Applications: toxic comment detection and langauge translation.

                     Co-author: Nithum Thain. Duration: 55 min


    

    

        


            video |

            slides |

            code





            


            A neural network trained to play the game of Pong from just the pixels of the game.

            Uses reinforcement learning and policy gradients. The approach can be generalized to

            other problems involving a non-differentiable step that cannot be trained using traditional supervised learning techniques.

            A practical application: neural architecture search - neural networks designing neural networks. Co-author: Yu-Han Liu. Duration: 40 min


        Tensorflow and deep reinforcement learning, without a PhD

        













    Quick access to all code samples:

    

        

                    tensorflow-mnist-tutorial


                    dense and convolutional neural network tutorial

                

        

            tensorflow-rnn-tutorial


            recurrent neural network tutorial using temperature series

        

        

            tensorflow-rl-pong


            "pong" with reinforcement learning

        

    

    

    

        tensorflow-planespotting


        airplane detection model

    

    

            conversationai: attention-tutorial


            Toxic comment detection with RNNs and attention

        

    












*Disclaimer: This is not an official Google product but sample code provided for an educational purpose*