fastai

My second attempt at Lesson 2 of “Practical Deep Learning for Coders” by fast.aiI’m working through Lesson 2 of the marvelous “Practical Deep Learning for Coders” course by Jeremy Howard...

My first attempt at Lesson 2 of “Practical Deep Learning for Coders” by fast.aiI’m a math adjunct and aspiring data scientist working through the “Practical Deep Learning for Coders”...

My experience with the first lesson of the excellent “Practical Deep Learning for Coders” by fast.aiFor the last six months, I’ve been working to transition from being an adjunct math...

When Pytorch-transformers meets FastaiPhoto from Kapa65 at PixabayIntroductionIf you follow the trend of deep learning and especially NLP, it would be impossible that you did not hear about Fastai...

I recently competed in a local AI competition where the challenge involved human pose classification with 15 different classes. This was my first ever AI competition and the experience was humbling....

An Overview of Lesson 1: Introduction to Random Forest of Machine Learning Course from Fast.aiOn a meetup that I attended a couple of months ago in Sydney, I was introduced to an online machine...

After creating and cleaning a dataset from scratch with Pandas in our first article, we are now going to train an AI with our datas to distinguish several elements in movie snapshots.Gérard...

Another case study and some thoughts on domain knowledgeI showed the result of using collaborative filtering to predict the interaction strength between a drug and its target in the first blog post...

ML to RL, without a PhDI decided to write a post I’ve been wishing existed for a long time. A simple collection of the best resources for those who always wanted to understand machine learning....

Learn to classify blood smear images using a high-level deep learning environmentJimmy Chan/Pexels free imagesAfter the Lister Hill National Center for Biomedical Communications (LHNCBC), part of...

In this article, I will show you step by step, how to build your own real time hand keypoints detector with OpenCV, Tensorflow and Fastai (Python 3.7). I will be focusing on the challenges I faced...

Boost your Image Classification ModelImage classification is assumed to be a nearly solved problem. Fun part is when you have to use all your cunning to gain that extra 1% accuracy. I came across...

Building a serverless image classifier using fast.ai, AWS Sagemaker and Lambda.Ever since the “Not Hotdog” app featured on HBO’s Silicon Valley, and Tim Anglade’s comprehensive article on...

Using the new Innotater tool to annotate data for a better predictive model.Many machine learning projects start with a Jupyter notebook, and the first few lines of the notebook load the training...

Classifying images of oil palm plantations using fast.aiPhoto by Alexander Naglestad on UnsplashThe Women in Data Science in collaboration with their partners initiated the WiDS datathon. The...

Photo by Blake Weyland on UnsplashIf you’re building an image classifier these days, you’re probably using a convolutional neural network to do it. CNNs are a type of neural network which build...

Learning Deep Learning — Step 1Finding a home for learning with Fast.aiCourtesy of http://neuralnetworksanddeeplearning.com/chap5.htmlIn late 2017, I stumbled across Fast.ai while looking to...

Deep learning to predict if a machine will be infected by malware.Kaggle recently finished the competition “Microsoft Malware” which asks you to predict if a computer is infected. The...

Interview with Senior Research Scientist at the United States Naval Research Laboratory: Dr. Leslie SmithPart 23 of The series where I interview my heroes.Today, I’m super excited to be talking...

As part of my 2019 resolutions, I have decided to study Deep Learning through Fastai’s MOOC. Lesson 1 focuses on image classification and creating a State of the Art (SOTA) classifier. As homework,...

Recently I have tried fast.ai deep learning library and would like to share my experience.First, my background — not to show how cool/bad I am, but because it will mostly relevant to people who...