Testing for the Data Scientist

As I delve into data science more myself, I am surprised at the unfortunate inattention paid to the lessons already learned by software engineers, particularly around testing and clean code.

Quick Tip: Image Resize Prep for Training

When designing and working with neural networks, a common requirement is having a fixed image dimensions for inputs... By handling the image resizing beforehand, the training phase will be able to progress without as much overhead and thereby allow for tighter feedback loops.

Eye Tracking: Activation Functions

While experimenting with multiple architectures, I took the opportunity to step back and consider how I might confine the output of the neural network to be a bit more specific to the GazeCapture of iOS devices.

Eye Tracking Update: Neural Network Architecture and Loss Functions

Background As a part of my graduate studies at Regis University, I have had the opportunity to begin exploring my own project during my Deep Learning class. (Data Source) By using this data set before my practicum (Spring 2019), I hope to not only explore and model some interesting data

GPUs or CPUs for Deep Learning?

Photo [https://www.pexels.com/photo/blur-close-up-computer-device-343239/] by Jordan Harrison [https://www.pexels.com/@jord] from Pexels [https://www.pexels.com/] The repurposing and expansion of GPUs for neural network calculations has revolutionized the possibilities of deep neural network architectures and made large, general-purpose models like Inception and RestNet computationally