Introduction
A natural progression in the field of computer vision following unprecedented progress in image classification tasks is towards video and video understanding, especially how it relates to identifying human subjects and activities. A number of datasets and benchmarks are being established in this area1.
[Read More]
Recommendation System for Cookbooks
Case Study Using Amazon Book Reviews
Introduction Ever since I started watching Great British Baking Show, I added three books to my ever-increasing collection of cookbooks. Do I bake? No sir, I do not! At least not very well. I am not alone in this obsession with cooking shows, and cookbooks. According to NBCNews.com, roughly 18...
[Read More]
Classifying Car Images Using Features Extracted from Pretrained Neural Networks
Is that a Corvette?
Introduction According to 2018 Used Car Market Report & Outlook published by Cox Automotive, 40 million used vehicles were sold in the US last year. This represents about 70% of the total vehicles sold. A good portion of these sales already use online resources along various stages of purchasing: searching,...
[Read More]
Predicting Tomorrows Gold Price
Do we have a market advantage?
Introduction Central banks across the world maintain gold reserves to guarantee the money of their depositors, foreign-debt creditors, and currency holders. Central banks also use gold reserves as a means to control inflation and strengthen their country’s financial standing. In addition, gold is used by finance companies, global institutions, money...
[Read More]
An Introduction to Objective Functions Used in Machine Learning
What is the difference between Maximum Likelihood & Cross-Entropy?
Developing machine learning applications can be viewed as consisting of three components [1]: a representation of data, an evaluation function, and an optimization method to estimate the parameter of the machine learning model. This is true for supervised, unsupervised and reinforcement learning. The primary focus of this article is the...
[Read More]