Updated talks on Machine Learning and Deep Learning

I’ve just spent a few days at the AWS Loft in Stockholm, where I delivered 5 talks on Machine Learning and Deep Learning. All of them have been updated quite a bit and I figured it would be convenient to share them in one place, so here they are.

As always, happy to answer any question that you may have :)

An Introduction to Machine Learning with Python and scikit-learn

Topics: introducing and demonstrating Linear Regression, Logistic Regression, Decision Trees, K-Means and Principal Component Analysis.

An Introduction to Amazon SageMaker

Topics: the SageMaker service — Using built-in algorithms — Demos with XGBoost and Blazing Text.

Deep Learning: concepts and use cases

Topics: An introduction to Deep Learning theory: Neurons & Neural Networks, The Training Process, Backpropagation, Optimizers — Common network architectures and use cases: Convolutional Neural Networks, Recurrent Neural Networks, Long Short Term Memory Networks, Generative Adversarial Networks.

This session was filmed and streamed on Periscope. Here’s the link.

Deep Learning on Amazon SageMaker

Topics: Built-in algos and environments for Deep Learning — Demo: image classification with the built-in algo — Demo: training ResNet on CIFAR-10 with Tensorflow and Tensorboard— Demo: training ResNet on CIFAR-10 with Apache MXNet and Hyper Parameter Optimization — Demo: building a custom container for Keras— AWS DeepLens.

MLOps with serverless architectures

Topics: Why? — A quick recap on Amazon SageMaker — A quick recap on serverless architectures — Open Source tools: AWS Chalice, Serverless Framework — Demos: retraining models automatically, pre/post-processing predictions.