In PyTorch, arrays can be also be written as Tensors, which is basically the same thing as an array in Python, only that Tensors can run on a GPU to increase speeds by over 100,000 times. This increase in computational speed is critical for machine learning programs to function efficiently in the practical world.

A black and white computer image is a “2 dimensional array” or “tensor of rank 2” of numbers, with each number between 0 and 255. …


Source: Google Images; Shutterstock.com

Here I summarize how to identify and address ethical issues of deep learning from the book “Deep learning for Coders with fastai and PyTorch” by Jeremy Howard & Syvain Gugger.

A four step process is recommended to identify and address ethical issues of deep learning:

  1. Analyze a project you are working on.
  2. Implement processes at your company to find and address ethical risks.
  3. Increase diversity.
  4. Support good policy.

1. Analyze a Project You Are Working On

To not miss important issues when considering ethical implications of your work, you and your team must ask yourselvesthe right questions. …


Source: Google Images

Although data labeling is also essential for other types of machine learning applications such as natural language processing, speech recognition, and more, for this article we will focus on data labeling for Computer Vision. Specifically:

(1) What is data labeling for computer vision?

(2) Picture examples of data labeling for autonomous vehicles and bird watching

(3) Different options to get data labeling done!

(4) Links to data labeling sources

(1) What is data labeling for computer vision?

Data labeling for computer vision is when we draw a digital outline around objects in a picture so that the computer can distinguish…


Source: google images: Air & Space Magazine

The year is 2021. From a theoretical idea originating from 1943, deep learning software and hardware has developed over the decades to become a useful tool in our everyday lives. Below I share both deep learning applications that already are in use today and those that are being developed and tested as we speak to be used in the coming years.

Part 1: Deep learning application that already are in use today

Computer vision This type of application involves computers processing, analyzing, and making sense from visual images. For example, iPhone uses facial recognition to unlock your phone.

Natural Language Processing (NLP) This type of application involves speech recognition, answering questions, classifying document, search engines and more. Virtual Personal Assistants is one type of this kind of deep learning application that can be found in your everyday life: Xiaomi, Siri on your iPhone, Amazon Alexa, Google Assistant, Google Home, etc.

Medicine Deep learning programs are now more accurate than radiologists at…


www.igenesiis.com

It was 1989 when I was 12 and all the kids in my neighborhood got very comfortable allowances to buy the things they wanted. My parents were strict and did not give me an allowance. This motivated me to make money. So my first business was making bracelets from discard surfing wetsuits. And a few months later my parents caught me and banned me from doing that business. A few weeks later, when they had forgotten about the incident, I soon started another business. And then a few months later, I was caught again and banned from doing that business…

Albert Energy

American living in Shanghai, China for 20 years. My passion is empowering people to turn their innovative ideas into meaningful and sustainable businesses!

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store