Using deep learning to measure movement impairments
Our PLOS Biology paper explores how video models can score motor impairments and identify movement features that conventional assessments might miss.
Blog
Building the software powering Coastline Academy.
Building an insanely fast image classifier on Android with MobileNets in TensorFlow
Part two of a two-part series: It’s like hot dog not hot dog, but for roads
Creating insanely fast image classifiers with MobileNet in TensorFlow
“It’s like hot dog not hot dog, but for roads.”
Super simple distributed hyperparameter tuning with Keras and Mongo
Distribute Keras training jobs across workers with a controller and a MongoDB jobs collection.
Let’s evolve a neural network with a genetic algorithm—code included
Use a genetic algorithm to tune a neural network’s hyperparameters, with code and a comparison against brute force search.
Five video classification methods implemented in Keras and TensorFlow
Exploring the UCF101 video action dataset
Training a deep learning model to steer a car in 99 lines of code
The magical power of deep learning in 2017.
Continuous video classification with TensorFlow, Inception and Recurrent Nets
Part 2 of a series exploring continuous classification methods.
Continuous online video classification with TensorFlow, Inception and a Raspberry Pi
Or, using convolutional neural networks to identify what’s on TV
Reinforcement learning in Python to teach an RC car to drive itself — Part 3
Simulating the real world
Reinforcement learning in Python to teach a virtual car to avoid obstacles — part 2
Looking at loss, parameter tuning, and next steps
Using reinforcement learning in Python to teach a virtual car to avoid obstacles
An experiment in Q-learning, neural networks and Pygame.