Published in Towards Data Science·PinnedMember-onlySampling Large Graphs in PyTorch GeometricGraph Deep Learning techniques on large graphs — Sometimes we encounter large graphs that force us beyond the available memory of our GPU or CPU. In these cases, we can utilize graph sampling techniques. PyTorch Geometric is a graph deep learning library that allows us to easily implement many graph neural network architectures with ease. The library contains…Deep Learning6 min readDeep Learning6 min read
Published in Towards Data Science·Feb 3, 2021Member-onlyAdversarial Eyeglasses to Trick Facial RecognitionI recently read a paper by Sharif et al. that describes a general framework for adversarial example generation and they utilize eyeglass frames affixed to people’s faces to trick a facial recognition classifier. …Deep Learning5 min readDeep Learning5 min read
Published in Towards Data Science·Jun 15, 2020Member-onlyAI Lesson for Teachers, Teens, and Everyone In BetweenMy goal is to outline a lesson that any teacher can use in the classroom or any person interested in a very high level understanding of how AI works can walk through. This is not meant to be an exact representation of how AI truly works, but simply give intuition…Machine Learning6 min readMachine Learning6 min read
Apr 14, 2020Member-onlyGenerate Faces that Trick Facial Recognition with GANs in PyTorchMy goal here is to create an easily adaptable framework to generate faces that look realistic, but also trick a facial recognition classifier. The example we will work through is the task of generating realistic faces that always classify as your face — despite them not being your face (or…Artificial Intelligence7 min readArtificial Intelligence7 min read
Published in Towards Data Science·Apr 11, 2020Member-onlyFinetune a Facial Recognition Classifier to Recognize your Face using PyTorchTricking facial recognition systems using adversarial attacks with GANs. — This is part of a series I am writing on tricking facial recognition systems using adversarial attacks with GANs. However, before we trick a facial recognition classifier we need to build one to trick. I personally want to build one that can recognize my own face. Instead of training a…Artificial Intelligence8 min readArtificial Intelligence8 min read
Published in Towards Data Science·Oct 19, 2019Member-onlyDeep Learning on Dataframes with PyTorchThe goal of this post is to lay out a framework that could get you up and running with deep learning predictions on any dataframe using PyTorch and Pandas. By any dataframe I mean any combination of: categorical features, continuous features, datetime features, regression, binary classification, or multi-classification. I may…Machine Learning9 min readMachine Learning9 min read
Published in Towards Data Science·Oct 9, 2019Member-onlyAutonomous Truck Simulator with PyTorch — finetuning and single shot detectorsThis is a continuation of a previous post where I do a full walkthrough of how to build an autonomous truck simulator using fast.ai, but ultimately these methods can work on any case where you need to finetune pretrained models or develop models that predict bounding boxes and classes together. …Machine Learning9 min readMachine Learning9 min read
Mar 29, 2019Simulating gene sequence analysis with Hidden Markov ModelsFor some reason I had an inkling to go back to HMMs recently and here was the result. I started with this article from Nature by Sean R Eddy on biological sequence analysis and gene identification. …Hidden Markov Models5 min readHidden Markov Models5 min read
Mar 29, 2019Member-onlyProductionalize analytics Flask app with Docker, AWS, and Google APIHopefully this can be useful to anyone looking to host a Flask app on AWS with Docker, but more specifically this will deal with many of the hurdles involved with putting this app into production while analyzing Google Analytics API data, visualizing with Plotly Dash, and version controlled with Amazon…Docker14 min readDocker14 min read
Published in DataDrivenInvestor·Jan 23, 2019Customize fast.ai to develop an in-game self-driving vehicle with American Truck SimulatorI want to give a big thanks to the fast.ai team for not only open-sourcing a fantastic library for deep learning but also providing the resources to learn it. I also want to thank pythonprogramming.net …Machine Learning17 min readMachine Learning17 min read
