GitHub - kmkolasinski/deep-learning-notes: Experiments with Deep Learning
Experiments with Deep Learning and other resources:
- keras-capsule-pooling - an after-hours experiment in which I try to implement Capsule pooling for images.
- max-normed-optimizer - an experimental implementation of an interesting gradient descent optimizer which normalizes gradients according to their norms. Contains various experiments which show potential power of this method.
- selu-regularization - a Keras Regularizer Layer which allows for forcing SELU like regularization on the model weights (Dense and Conv2D versions are provided). Selu was introduced as an activation function with special initialization method, those regularizers can be add to force the weight to preserve self normalizing property during the training.
- tf-oversampling - example with how to implement oversampling with tf.data.Dataset API.
Seminars on Deep Learning and Machine Learning
Seminars - contains a bunch of presentations I have gave at our company.
imgaug - Image augmentation for machine learning experiments.
Last year we held a machine learning seminar in our London office, which was an opportunity to reproduce some classical deep learning results with a nice twist: we used OCaml as a programming language rather than Python....
lab_getting_started.py Lab This library lets you organize TensorFlow machine learning projects. It is based on a bunch of utility functions and classes I wrote while trying some...
README.md TeleGrad Telegram bot to monitor and control deep learning experiments
README.md fluid_sim - Some flashy 2D fluid simulations
README.md Experiments with Adam This repo contains the scripts used to perfom the experiments in this blog post. If you're using t...
README.md PSLab-apps GUI Experiments for PSLab from FOSSASIA
README.md Linux kernel exploitation experiments This is a playground for the Linux kernel exploitation experiments. Only basic methods. Just for fun.
Mozilla plans to run four new Test Pilot experiments for the Firefox web browser in the coming two quarters.