John R. Pierce was an applied physicist who obtained a Ph.D. in electical engineering from California Institude of Technology in 1936. Immediately after, he went to work for Bell Telephone Laboratories, where he spent 35 years, eventually becoming the executive director of the Research-Communications Principles Division. Pierce was known for helping develop early forms of communications satellites, … Continue reading Book Review: An Introduction to Information Theory: Symbols, Signals and Noise →

Previously, I've posted short reviews and photos of books I've read on my Facebook page. In order to centralize these and perhaps reach a few more people, I've decided to move them to my blog! Your Brain is a Time Machine, by Dr. Dean V. Buonomano. Dr. Buonomano is a professor of Behavioral Neuroscience in … Continue reading Book Review: Your Brain is a Time Machine →

This will be the first of a new kind of post on this blog. I'll be taking notes on research papers, which will ideally be informative and concise summaries of their contents. Overview This paper for this post is entitled Bayesian GAN, by Yunus Saatchi and Andrew Gordon Wilson. Looking at the abstract, this paper seems ambitious: casting generative … Continue reading Notes: Bayesian GAN →

  The code for this post can be found at this link. One can view it in HTML format here (which I recommend, since WordPress botches Jupyter notebook formatting). This Jupyter notebook was created to explore the dataset used in the Dog Breed Identification Kaggle competition. After this is accomplished, I will move onto another notebook, this time … Continue reading Kaggle’s Dog Breed Identification Competition (Part I): Data Exploration →

This Jupyter notebook can be found on my GitHub page (located at: https://github.com/djsaunde/GRiD/data_processing_tutorial). It appears that some of the images which I attempted to display will not, due to some WordPress issues. You may click on the link to the images which do not display to view them outside of this blog post. Introduction Python … Continue reading Data Processing in Python Using Pandas and Matplotlib →

To avoid extremely long and redundant blog posts, instead of writing notes on an entire chapter from Deep Learning, I will instead write about a chapter subsection or some topic I find interesting. Today's post is about the bias-variance tradeoff, a well-known problem in machine learning which involves minimizing two sources of error which prevent supervised learning … Continue reading The Bias-Variance Tradeoff →

Thus begins my notes on the third chapter of Deep Learning, entitled Probability and Information Theory. This chapter was more exciting to read than the last, but there is a similar amount of math notation. Like the last chapter, it contains mathematics and ideas which are fundamental to the practice of deep learning. P.S. This took way too … Continue reading Deep Learning Book: Probability and Information Theory →

I want to get familiar with the brian2 spiking neural network simulator; hence, this blog post. The code and Markdown-formatted comments were developed in a Jupyter notebook. Part I: Neurons Imports and Setup brian2 has a system for using quantities with physical dimensions. All the basic SI units can be used along with their standard prefixes, and … Continue reading brian2 Spiking Neural Network Simulator Tutorial →

word2vec: Tensorflow Tutorial In which I walk through a tutorial on building the word2vec model by Mikolov et al. I'll document justification for the code I write each step of the way. Much of the notes / images / code are / is copied or slightly altered from the tutorial. Imports Highlights This Tensorflow tutorial … Continue reading Word2vec: A Computationally Efficient Model for Learning Word Embeddings →