Sign in

Ritobrata Ghosh
Source: Author

A Hands-On Guide

How to Represent Any Boolean Function with Elementary Logic Gates


Digital electronics is probably the most impactful and widespread technology now. It forms the basis of all of the chips- from ARM microcontrollers to processors in cellphones, all the way to uberpowerful AMD Threadrippers. In all these cases, digital electronics reign supreme.

It is very useful to learn not only about basic principles but also how these principles and the components of Digital Electronics exactly form the basis of the modern world, i.e., how do we go from basic logic gates to fully functional computers.

Elements of Computing Systems

Digital Electronics is not only important because it is the base of the modern technology…

Photo by Joshua J. Cotten on Unsplash

A Better Kaggle

Lessons from A Recent Kaggle Discussion Grandmaster

When you head over to Kaggle’s hot and new Communities section, you might be a little disappointed. I was. I am, mostly.

Initially, I was excited that Kaggle was very thoughtful and considerate to introduce this feature. But soon, I found that the Communities were abused to stack up upvotes and were filled with spam. Kaggle is not at any fault here.

There was helpful content as well, but, sadly, they were in the minority. Communities were filled with aggregated Notebooks, aggregations of posts, and aggregations of other aggregations… You get the idea.

I did not like this. Moreover, I…

Photo by Icons8 Team on Unsplash

Amazing ML Podcasts

Podcasts to Keep You Updated on the Everchanging Field of AI


Podcasts are a great way to learn about novel fields and tools, as well as keeping yourself updated with the fields that you care about.

I also believe that podcasts which are mainly centered around interviews are a great way to learn about the rockstars and superheroes of the AI world. You get a glimpse of how they think, what are they working on, and howthey solved a particular problem.

I would also argue that the content you get access to by listening to podcasts is very unique, and you cannot access them somewhere else.

In this post, I am…

Photo by Sixties Photography on Unsplash

Using Additional Data with Pictures in Vision Models

Guide on How to Use Additional Numeric Data with Images for Training a Convolutional Neural Network

[You can access a free version here (for non-Medium Members)]

This problem appeared to me as a question in a Kaggle Community forum. Someone wants to use location data along with pictures of houses to predict house prices. This is my take on how to do that and additional thoughts.

I am assuming that you are trying to predict the prices of the houses where the pictures of the houses are among the inputs.

This can be accomplished by putting the prices as targets y. And then have the NN predict the price for previously unseen house pictures as y^.

Photo by Uriel SC on Unsplash

Getting Started with Transfer Learning

Guide on How to Begin Choosing Pretrained Models for Solving a Problem

[You can access a free version here (for non-Medium Members)]

When it comes to Deep Learning models, there are many architectures, and then there are variations of those architectures. Then there are hyperparameters to tune. It is easy to feel a bit overwhelmed when it comes to available options and choosing from them to solve the problem at hand. However, you shouldn’t feel helpless. These are some general advice to get started with using pre-trained architectures for transfer learning, or using an architecture for training the model from scratch-

It is not as hard as it sounds. Because all those…

Photo by USGS on Unsplash

Taking Julia For A Test Drive

Scratching The Surface of Julia and Pluto

I started taking a course online and it was taught through Julia. Although I have no prior experience in Julia, it was easy for me to pick up things quickly- as I have prior programming experience, and most importantly- Julia is designed to be easy to write.

Pluto: An Aesthetic Environment for Writing Julia

Julia works through REPL in the command line. I hear that Visual Studio Code’s extension for Julia is also great. But it is best to use the Pluto for a task like image analysis and to be able to get instant feedback is something really helpful for it.

Photo by Antoine Dautry on Unsplash

A Clear, Straightforward Answer.

It was one of the burning questions that I had before I started my journey in Data Science. And it is one of the questions that occupy the minds of people who are seriously looking into beginning their Data Science journey. In this post, I provide you with a clear answer.

I am not a professional data scientist. But I have walked the first bits. And I am a firm believer of the saying-

“You are the best person to guide the people who are right one step behind you”.

Having come from a Physics background, I had solid foundations…

Setting up Google Colaboratory (Colab) for the Deep Learning MOOC comes with its quirks. But the task is fairly straight forward.

Step 1: Setting Up Colab

I will assume that you have already set up Colab. It is as simple as navigating to the Google Colab website and logging in with your Google account.

When you open Colab, you will be prompted to open a notebook. Choose “GitHub” and type in fastai/course-v3 the search box. Hit search and you will be shown notebooks in the repository. Make sure the master branch is selected.

Choose “GitHub” and type in fastai/course-v3 the search box

Open the one you intend to, and that’s all!

Step 2: Changing Runtime Type

Navigate to…

Photo by Maarten van den Heuvel on Unsplash

Using a Machine Learning Algorithm for New Investment

“It is difficult to make predictions, especially about the future.”

~Niels Bohr

Everything is better interpreted through data. And data-driven decision making is crucial for success in any industry.

And it has been true since time immemorable. The difference now is that we have, for better, developed a healthy outlook to data, and we have much more data available to us than previous times. And we have, in our disposal, computing powers previously unimagined.

In this situation, the computing power and the data should be leveraged to make better decisions to solve business problems.

In my project, I chose to…

Photo by Emile Perron on Unsplash

This article is meant to be a reference sheet for basic operations involving files in Python.

If you do not primarily work with files in Python, and need to do it from time to time, this is for you.

Text File

  • Open a file:
with open(‘path/file.txt’) as text_file:
  • Read the whole document-
with open(‘path/file.txt’) as text_file:
text_file_content =
# do something with the content, like printing it
  • Read line by line-
with open(‘path/file.txt’) as text_file:
text_lines = text_files.readlines()
for line in text_lines:
# do something with the lines, like printing them
  • Read the first line only-
with open(‘path/file.txt’) as text_file…

Ritobrata Ghosh

Deep Learning Consultant | Deep RL | GANs | Computer Vision | Deep Learning | Machine Learning | Math Geek | Bibliophile

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