Design Professional Mails using Flask!

Have you ever wondered how companies like Medium send Emails to users that look so fancy that it is basically a website in a mail? And on top of that — they send millions of Emails to their Massive user-base in minutes DAILY!!! All Customized to the user's interests.


They have Images, Subscribe Buttons, Tables, GIF’s, Booking Buttons, Headers (in the center), Logos, Amazing Fonts, Socials, and god knows what else.

So let’s make our own “Automatic-Pro-PythonCode-Email-Sender-Bot…ish”

Let’s write a few lines of Python code that will…

Training on your own Data

This will be a practical, end-to-end guide on how to build a mobile application using TensorFlow Lite that classifies images from a dataset for your projects.

This application uses live camera and classifies objects instantly. The TFLite application will be smaller, faster, and more accurate than an application made using TensorFlow Mobile, because TFLite is made specifically to run neural nets on mobile platforms.

We’ll be using the MobileNet model to train our network, which will keep the app smaller.

Getting Started


  1. Python 3 .5 or higher python3 -V
  2. Tensorflow 1.9 or higherpip3 install — upgrade tensorflow

Also, open the…

In Reinforcement Learning, the agents take random decisions in their environment and learns on selecting the right one out of many to achieve their goal and play at a super-human level. Policy and Value Networks are used together in algorithms like Monte Carlo Tree Search to perform Reinforcement Learning. Both the networks are an integral part of a method called Exploration in MCTS algorithm.

They are also known as policy iteration & value iteration since they are calculated many times making it an iterative process.

Let’s understand why are they so important in Machine Learning and what’s the difference between…

MCTS For Every Data Science Enthusiast

The Games like Tic-Tac-Toe, Rubik’s Cube, Sudoku, Chess, Go and many others have common property that lead to exponential increase in the number of possible actions that can be played. These possible steps increase exponentially as the game goes forward. Ideally if you can predict every possible move and its result that may occur in the future. You can increase your chance of winning.

But since the moves increase exponentially — the computation power that is required to calculate the moves also goes through the roof.

Monte Carlo Tree Search is a method usually used in games to predict the…

#4 Research Paper Explained

DeepMind and other universities has published many End to End Reinforcement Learning papers that are used for problems that can be solved by a single agent. End to End RL algorithms learns both feature representation and decision making in the network by taking pixels as the input and the controls as output.

Previous Work: Single player game Source

The real world contain problems that needs multiple individuals acting independently but still collaborating together to achieve a single goal. From playing games like football or basketball to landing a rocket on the moon, a team of individuals works together following a strategy to complete the faster, safer…

#3 Research Paper Explained

Google is famous for their cutting edge technology and projects including Self Driving Car, Project Loon (Internet balloon), Project Ara and the list goes on. But alot of research goes behind the scenes, which yields in some interesting research papers that literally gives us access and insight on these fun experiments. Encouraging us to replicate the experiments by ourselves and build further to push the boundaries.

Project Ara | Source

The Learning Robots Project by GoogleX has published QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation that tries to master the simple task of picking and grasping different shaped objects. …

#2 Research Paper Explained

The doors this paper unlocks for the machine learning community are amazing. The tiny network actually plays Atari game with only 6 neurons comparable and occasionally superior making the previous networks look like jokes. And the best part is that the code is open source on GitHub for everyone to play with. So, let’s get to it…


How is it Possible!!!

We already know that the Deep Reinforcement Learning network that play atari games are basically a dense deep neural network has both the responsibility of internally learning to extract features from the image with the first layers by mapping pixels to intermediate representations…

#1 Research Paper Explained

Mix & Match — Agent Curricula for Reinforcement Learning [ arxiv ]

The Reinforcement Learning Techniques that are used nowadays are very quick and give immediate results for less complex environments using the gradient based policy optimisations.

The Gradient based policies are competitive and not collaborative.

So what if we need long lasting results for more complex environments having agents with complex tasks to perform.

There are many world environment where we do not have the ability to modify the environments and performing Reinforcement Learning on the real world tasks are really time consuming. …

Everything you need to know…

At the time of writing this article TensorFlow 1.9 is not updated on their official website but TensorFlow 1.9 rc-0 is out and released on their GitHub.

The Major and Improvements 🚀

  1. Update your tf.keras to Keras 2.1 API.
  2. Please inherit tf.keras.Model because tfe.Network is deprecated now.
  3. Adding support of core feature columns and losses to gradient boosted trees estimators.
  4. The Bijectors API supports broadcasting for Bijectors with new API changes.
  5. Layered variable are changed in the following conditions

Might Break Here

Replace variable_scope('', ...) by variable_scope(tf.get_variable_scope(), ...) if you are opening variable scopes.

TensorFlow API Cheetsheet

In this article I really want to give a look at the TensorFlow.js APIs and understand the library as a whole and understand what are the amazing things it has to offer to the machine learning community.

I know this article should be 5 minutes long but don’t worry it will not take more than 5 minutes to understand the obvious APIs and even though many of them are very obvious from there names, it was important for me to keep it beginner friendly.

I have kept the rest of the article as to-the-point as possible with examples. …


Freelance Writer. React developer. Deep learning/AI Electronics 📩

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