Solving an MDP with Q-Learning from scratch - Deep Reinforcement Learning for Hackers (Part 1)

It is time to learn about value functions, the Bellman equation, and Q-learning. You will use all that knowledge to build an MDP and train your agent using Python. Ready to get that ice cream? »
Author's profile picture Venelin Valkov on reinforcement-learning

Introduction to Reinforcement Learning - Deep Reinforcement Learning for Hackers (Part 0)

In these series, you will build and train your own agent while learning about Deep Neural Networks, Q-learning, Bayesian Reinforcement Learning and some of their friends. All of this implemented in Python using PyTorch. Shall we? »
Author's profile picture Venelin Valkov on reinforcement-learning

Credit Card Fraud Detection using Autoencoders in Keras - TensorFlow for Hackers (Part VII)

How Anomaly Detection in credit card transactions works? In this part, we will build an Autoencoder Neural Network in Keras to distinguish between normal and fraudulent credit card transactions. »
Author's profile picture Venelin Valkov on data-science

Human Activity Recognition using LSTMs on Android - TensorFlow for Hackers (Part VI)

Ever wondered how your smartphone, smartwatch or wristband knows when you're walking, running or sitting? We will train an LSTM Neural Network (implemented in TensorFlow) for Human Activity Recognition (HAR) from accelerometer data. The trained model will be exported/saved and added to an Android app. We will learn how to use it for inference from Java. »
Author's profile picture Venelin Valkov on data-science

Making a Predictive Keyboard using Recurrent Neural Networks - TensorFlow for Hackers (Part V)

Have you ever wondered how predictive keyboards work? You know them - those you use or your iOS or Android phone. Let's build a model using a Recurrent Neural Network using Keras that does just that! »
Author's profile picture Venelin Valkov on data-science