README.md

ML Bootcamp 2019

You can find the resources, notes and links that will be used at the Machine Learning Bootcamp here.

Day 1

• Intro to ML
  • Sides - https://docs.google.com/presentation/d/1g8VVLMVfkRwMXkp-zwOD2aF5SPupGqqwQ1uE9yI_r9U/edit?usp=sharing
• Problem framing
  • Slides - https://docs.google.com/presentation/d/1XjXcpq-N4jfxPhHiLIbLwWP71rWSq3-XCGlFQ2Shdo4/edit?usp=sharing
• Data preparation and Feature Engineering
• Linear and Logistic regression with scikit learn (theory + hands on)
  • Slides - https://docs.google.com/presentation/d/1KoacG4Ddhq6asCK7F5SJmdkRtJ2YTTM6QOubg1sKEWM/edit?usp=sharing
  • Linear - https://colab.research.google.com/drive/1ekd7raM6lBgRYzrQTntXD1gegHlubXYK
  • Logistic - https://colab.research.google.com/drive/1Qva6AwESqgjHkviIVwjUgy-NGRXoa-R0
• Loss function / Gradient Descent / Backpropagation
  • Colab - https://colab.research.google.com/drive/1WgkY0ZfALF6URdMbvEtVVojZS75VJ-dD

Lunch Break

• Intro to Tensorflow (sessions, graphs and basic principles + hands on)
  • Slides - https://docs.google.com/presentation/d/1sLRTZIOFyGkQ4RJgu0BmMes3Fujc1GLQ_BBo1ou2oD0/edit?usp=sharing
  • TF Basic - https://colab.research.google.com/drive/1-pIkqipJKiYU01cH3U2ndrCnnaaL_0hR
• First Neural Net with Tensorflow and Intro to Keras(training, testing with different hyper params, loss functions etc)
  • Colab - https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/keras/basic_classification.ipynb
  • Neural Network Playground - https://playground.tensorflow.org/

Tea Break

• Generalizing (overfitting, underfitting, regularization etc.)
  • Colab - https://colab.research.google.com/drive/16jp1Jq3KJt236JeSHbMWHLvXbJWi6Wfs
• Feature crossing
• TF Estimators
• Practical exercise : New York taxi fare prediction
  • Challenge - https://www.kaggle.com/c/new-york-city-taxi-fare-prediction
• Enroll to QwikLabs Quest "Baseline: Data, ML, AI"
  • Sign in to Baseline: Data, ML, AI using the given Study Jam Access Code

Day 2

• Recap of day 1
• New York taxi fare prediction solution
• Embeddings
• How to use GCP for ML(train New york taxi fare model on ML Engine)

Lunch Break

• Convolutional neural networks (practical: an image classification)
  • Slides - https://docs.google.com/presentation/d/1O2Fny8zpbmDNjHwVUOjYmwfiu-1n9XJv8PwQ8XDV92g/edit?usp=sharing
  • Colab - https://colab.research.google.com/drive/1Kof7J312znH1NAMrjMhpbh8fZ0AXxSS2
  • CodeLabs - https://codelabs.developers.google.com/codelabs/mlkit-android-custom-model/#8
• Artistic style transfer
• Basic intro to RNN/LSTMs and their use cases
  • Slides - http://bit.ly/2XfNYpb
  • Colab - https://colab.research.google.com/drive/1p00DTA2S2vskvG2akTxLRfmnPh2p3S-v
• Convert the image classification model (built above) and deploy on Firebase
• ML Qwiklabs