Programming 

Artificial Intelligence, Machine Learning, Deep Learning, and Data Science — What’s the Difference?

Answer: Deep learning is a subarea of machine learning which is a subarea of artificial intelligence. Data science is an interdisciplinary area that combines all of those with math and programming skills to extract useful insights from data. “I’m trying to understand how the area of skills are related to each other, and one is a dependency of another. I hope you clarify for me where to start and how the path looks like. I know it’s a complicated question.” — Barakah, Python Freelancer Course Member Let’s start with a…

Read More
java 

Top 5 Data Science and Machine Learning Courses to Learn Online – Best of Lot

Many programmers and Computer Science graduates are moving towards Data Science and Machine learning hoping for better pay and career opportunity and there is a reason for it. Data Scientist and Machine Learning Specialist have been ranked the number one job on Glassdoor for last a couple of years and the average salary of a data scientist is over $120,000 in the United States according to Indeed. Data Science is not only a rewarding career in terms of money but also it provides the opportunity to solve some of the world's most…

Read More

Depthwise separable convolutions for machine learning

Convolutions are an important tool in modern deep neural networks (DNNs). This post is going to discuss some common types of convolutions, specifically regular and depthwise separable convolutions. My focus will be on the implementation of these operation, showing from-scratch Numpy-based code to compute them and diagrams that explain how things work. Note that my main goal here is to explain how depthwise separable convolutions differ from regular ones; if you’re completely new to convolutions I suggest reading some more introductory resources first. The code here is compatible with TensorFlow’s…

Read More
MatLab 

Stack Abuse: Python for NLP: Neural Machine Translation with Seq2Seq in Keras

This is the 22nd article in my series of articles on Python for NLP. In one of my previous articles on solving sequence problems with Keras, I explained how to solve many to many sequence problems where both inputs and outputs are divided over multiple time-steps. The seq2seq architecture is a type of many-to-many sequence modeling, and is commonly used for a variety of tasks such as Text-Summarization, chatbot development, conversational modeling, and neural machine translation, etc. In this article, we will see how to create a language translation model…

Read More
MatLab 

Your Digital Pinball Machine

I’ve had something of an obsession with digital pinball for years now. That recently culminated in me buying a Virtuapin Mini. OK, yes, it’s an extravagance. There’s no question. But in my defense, it is a minor extravagance relative to a real pinball machine. The mini is much smaller than a normal pinball machine, so it’s easier to move around, takes up less space, and is less expensive. Plus you can emulate every pinball machine, ever! The Virtuapin Mini is a custom $3k build centered around three screens: 27" main…

Read More