In this article, Manhattan and Euclidean Distance, two way of measuring distance and performance in deep learning, is explained in simple terms. It is a beginner, basic guide to machine learning distance functions and cost functions. As always our content is beginner friendly. Don’t use Medium? Subscribe for free content and notifications whenever we publish. Prefer to watch a Youtube tutorial instead? Scroll all the way down for our companion study video on Youtube. Your claps are greatly appreciated and help pay for our bagels :)

Machine learning is an interdisciplinary field (computer science, engineering, statistics, math). There are…

Understanding List Comprehension This post uses a lot of Python list comprehension which is more concise than Python loops. If you need help understanding Python list comprehension type the following code into your interactive python console (on Mac launch terminal and type python after the dollar sign $ to launch). Python code:

sample_list = [1,2,3,4,5][i*i for i in sample_list]

This code first assigns [1,2,3,4,5] to a variable called sample_list. In the second statement, the use of list comprehension, the keyword ‘for’ will be evaluated, in this case we will display ‘i’, each item in the list, for i in…

In this post, we highlight some of the best AI projects around the world. Enjoy. Hope they serve as inspiration and motivation for your AI projects.

State-of-art demo : Next Rembrandt AI generated Rembrandt painting.

The best in class example of AI generated art.

AI created fine art — Next Rembrandt

Check it out on our curated list or the original source.

Living Portrait : One Shot Learning Converting Oil Painting to 3D

Want Harry Potter style magical painting? Where the Fat Lady greets as you enter the living quarters through the forever changing staircases? Samsung’s Living Portrait shows you a hyper realistic Mona Lisa smiling, frowning looking very much alive. And she’s beautiful (see the middle portrait, which really surprises us).

Dear readers, Uniqtech has been doing really well on Medium and now we are a part of Google Startup Program and Y Combinator Sprint we are launching two self servicing, AI enabled features February and March. BETA testers welcome! once logged in, you can message us, ask us questions about tutorials, articles, advice, tips, give feedback.

The platform is programmed Xmas 2020, the same time we welcomed four talented Stanford interns to participate in our learning journey. Each of them successfully made their first Machine Learning model in Google Cloud.

Remember to read our disclaimer and note that users are not compensated for feedback. Though free developer perks, stickers coming soon. Did you encounter hardship in your tech career due to COVID-19? We’d like to hear your stories.

Alternative Title: understand regularization in minutes for effective deep learning. All about regularization in Deep Learning and AI

Regularizations prevents model overfitting by restricting parameter freedom. This is a beginner friendly regularization formula deep dive. We write beginner friendly tutorials: Softmax, Natural Language Processing, Cross Entropy Loss and GPT-3 model strengths and GPT-3 weakness.

Read the full disclaimer, basically our tutorials are for educational purpose only. We are NOT responsible for any commercial, production use nor do we advise it. All articles are exclusively published on our Medium and subdomains. No repost, no scraping. Thanks.

We will discuss regularization methods…

GPT-3 can’t save you today. GPT-3 by OpenAI (private beta) dazzles the world in 2020 with incredible demos like generating SQL query using plain English, writing code, and doing what seems like machine comprehension. Yes comprehensions are even hard for humans (think of SAT and GRE). We talked about this exciting news in our article GPT-3 past present future. We also wrote about NLP fundamentals in this our Getting Started with NLP article. It is very important for us to follow up and write about what GPT-3 cannot do. Limitations, weakness, mistakes. It is a bit hard without access to…

GitHub’s Codespaces (a derivation is VSCode in the cloud) has the potentially to completely change your developer workflow! Here are some cool things you can do with Github’s new online coding environment. Thanks to the power of its new owner Microsoft, Github has powered up its code editing offerings. Follow us for more cool articles like this about modern programming.

Our articles go through continuous development, continuous writing. Any feedback is welcome. We write all kinds of programming, data science, machine learning and deep learning articles. …

It used to be mandatory to be a statistician to be a data scientists. While stats knowledge is still helpful, these practical data science tasks are now must-haves for job applications and data analytics interviews. How many do you know? No worries, keep this list in mind. We will have tutorials that address each of these categories. Subscribe and follow us for updates.

  • Supervised Learning: classification tasks, probabilities, expected values, maximum likelihood, most likely outcomes.
  • Unsupervised learning: clustering, grouping similar demographics or behaviors together, segmentation
  • Similarity: similarity metrics, distance functions, identify similar customers, groups, characteristics, demographics
  • Regression: best fit line…

Jaccard Similarity is an easy, intuitive formula that is very powerful in many use cases including object detection in image recognition, classification, and image segmentation tasks (instance detection). This article is modeled after our popular machine learning, deep learning articles:

Most of the visuals and formula can be found on wikipedia.

As always, we first present the formula then provide intuitive, easy-to-understand explanations followed by real life examples!

Jaccard Similarity Formula

“The Jaccard index, also known as Intersection over Union and the Jaccard similarity coefficient (originally given the French name coefficient de communauté by…

Thanks for being a subscriber. Have you heard of OpenAI’s GPT-3? Simply put, it may be the most exciting tool for Natural Language Processing (NLP) in 2020. It’s the hottest and trendiest. In this NEW article, we give an overview of the model, use case, and metadata. More details on the paper coming soon! Hope it saves you time.

[NEW] Our take on #OpenAI GPT-3 Past, Present and Future of AI and NLP #GPT3 #DeepLearning #AI #Tesla #ElonMusk #NLP

Like what you read? Buy us a cup of ☕️


Learn data, machine learning skills w/ us. We’d like to hear from you! Like what you read? Tip us

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