Category: Machine Learning

The Buddhabrot
Deep LearningHard Sciences StudyMachine Learning
June 21, 2020 1 Comment

Chaos

Nietzsche, in the premise of Thus Spoke Zarathustra, stated Eternal Return, an idea that all things in the universe will recur and all events in one’s life will repeat again, and again, ad infinitum1. Nietzsche’s world was a deterministic one, Newtonian, with tangible objects, and countable sets. Hence, he viewed his universe like a deck of cards, bound to return to a particular shuffle infinitely on infinite shuffles. But all recurrences need not be perfectly self similar. Far older eyes have imagined universes in kalpas, forever repeating...

Continue reading
Computer VisionDeep LearningGithub Projects
January 5, 2020 Post a Comment

Conv Nets IV

In this project, I extend my CNN Advanced Architecture project to 3D images. The architecture is advanced in the sense that it is flexible and can read & build its architecture from JSON files. The 3D extension allows CNN3D classifier to tackle 3D tensors used heavily in scientific/medical imaging such as CT Scan images, which we will we working with in this repo. I have trained the LUNA16 dataset with the usual my CNN and then with CNN3D classes and noted that CNN3D outperfromed the predictions for...

Continue reading
Deep LearningHard Sciences StudyMachine Learning
September 6, 2019 2 Comments

Brachistochrone

Light is one of the most amazing phenomena in the Universe. It is pure energy and has zero mass. If you could experience a moment as a photon, you would experience eternity in that moment, for light experiences no time of its own (technically you’d experience nothing as psychological experience is time dependent, but lets keep the poetic tone). It is one of the primordial constituents of the Universe and is considered sacred in all religions, ditto physics. Among other things, a path of light is Brachistochrone....

Continue reading
Result: Starry NIght Over Rhone, Neural Style Transfer
Computer VisionDeep LearningFine Arts Study
July 14, 2019 1 Comment

Alla Prima

Last month I watched Loving Vincent. The movie was a story of Van Gogh post Saint Rémy, in his final year in Auvers-sur-Oise. The story reconstructed the lonely artist’s mental breakdown from the perspectives of people close to him, well at least they are there in his paintings. Aside from reconstruction in a sense of narrative, the movie was also reconstruction in material. The entire movie comprised of animations of reimagined Van Gogh’s paintings. It recreated 94 Van Gogh’s originals while creating about 67K oil paintings around...

Continue reading
Computer VisionDeep LearningGithub Projects
November 27, 2018 Post a Comment

Conv Nets II

In this project we automate learning CNN hyper-params. We test and improve my previous tensorflow implementation of CNN in here on Kaggle's facial expression dataset. Here I only deal with two label classes: Happy and Angry. Randomized Search for learning hyper_paramters such as learning_rate, momentum coefficient, etc and drop-out regularizer improved the default test prediction accuracy from 36% to 64%. This is a bit lower than 72% that we got from our SVM classifier. However, we will continue in following projects to see if we can beat...

Continue reading
Classical MLGithub ProjectsMachine Learning
September 18, 2018 Post a Comment

Gaussian Mixture Models

In this project we explore the Gaussian Mixture models. GMMs are universal approximators. This means that any probability density can be approximated to arbitrary precision using mixture of gaussian densities. We saw a glimpse of it in our Hypothesis Testing II project. GMMs are go-to models for unsupervised learning schemes and one of my favorite ML models. In fact, they utilize (usually) EM algorithm, which is an iterative method of estimating statistical parameters similar to and I belive, on par with, backpropagations in Neural nets. In this...

Continue reading
Computer VisionDeep LearningGithub Projects
September 14, 2018 Post a Comment

Conv Nets I

This project implements CNN class using the tensorflow library. I compare the accuracies gained by the ConvPool layers to the ANN architectures of the ANN-tensorflow repo. We find that adding only 2 ConvPool layers before the ANN architecture does automated feature engineering and significantly increases the classification accuracies as compared to the ANN only architectures....