This is the second part of this series. We will focus here on the price of bitcoin itself and the nature of sentiment analysis. This is still very academic so feel free to jump to part 3 for insights in the development framework and code. If you want to have Read more…
As seen in our previous article, our agent is able to imitate an autopilot, at least a little bit. Driving around in auto pilot sure is fun, but what would be the next step to enhance our agent ? Let’s try to make him learn via Reinforcement learning this time. Read more…
Introduction Transportation has always been a corner stone of progress, whether to convey goods from the Orient to Europe or enable the population to efficiently commute between cities. Tremendous progress has been achieved in the last century, thanks to breakouts in industry we are now blessed with trains cruising at Read more…
In this article we will play with the problem of the mountain car. So first, what is Q Learning ? Q learning is a form of learning through an agent doing stuff in an environment without using a model, there are no parameters to train, features and so on. The Read more…
Python Sc2 – Advanced bot Now, I had started to build my bot with the regular dentosal release, but it appears that this release is not working anymore with the latest starcraft versions. So I had to delete it and start over with the BurnySc2 that seems to be still Read more…
Python SC2 – Rule Based Bot Alright, So I was very excited about this small project. I have been playing starcraft for over 15 years and was always quite pationate about the game and still watch it from time time. Following the hype early 2019 concerning Alpha star : I Read more…
Here are my environment details : Python 3.7.8 Cuda 10.1 CUDNN v7.6.5 So.. The MNIST dataset is usually one of the first one people are using to learn about neural networks or machine learning as a whole. I remember solving this problem in matlab in the course taught by Andrew Read more…
In this article we will solve one of the easiest and most widely used example for deep learning. The cats Vs dogs classification. The goal is to train a model that will take a picture of a cat or a dog as input and tell you whether it is a Read more…
Summary of course topics Supervised learning – labeled data Linear regression Logistic regression Neural networks Support vector machines Unsupervised learning – unlabeled data K-means PCA Anomaly detection Special applications/topics Recommender systems Large scale machine learning Advice on building machine learning systems Bias and variance Regularization What to do next when developing a Read more…
Problem description and pipeline Case study focused around photo OCR Three reasons to do this 1) Look at how a complex system can be put together 2) The idea of a machine learning pipeline What to do next How to do it 3) Some more interesting ideas Applying machine learning to tangible problems Artificial data synthesis What is the photo OCR Read more…