Sign in

Zoheb Abai


first authors
First Authors: Emily M. Bender (Left), Timnit Gebru (Right)

In short — Authors have raised global awareness on recent NLP trends and have urged researchers, developers, and practitioners associated with language technology to take a holistic and responsible approach.

Where lies the Issue?

Most notable NLP trend — the ever-increasing size (based on its number of parameters and size of training data) of…

TSAI Classroom
This used to be a classroom. (There were exactly 64 chairs as in a game of Chess.)

Back in mid-2019, I was offered teaching assistantship positions at two different institutes. They were mostly distinct, barring few areas. Both had a similar motive to provide state-of-the-art knowledge to their paid learners. I knew it would be difficult for me to juggle both with my existing job. …

Have you watched this?

Or this?

Watch these videos as per your convenience and go through this blog to understand (without much mathematical sophistication) how we arrived at this stage.

If you have already watched these videos I totally understand your excitement. This breakthrough arrived in 2013 after…

For Data Scientists, Notebooks have become the ‘de facto’ tool while working on a project. Whether they perform EDA on the initially available dataset or begin with some data preprocessing steps or experiment with different models and libraries, notebook is the one they begin with. …

The meme from which it derived its name

Until 2014, CNN architectures had a standard design:

1. Stacked convolutional layers with ReLU activations 
2. Optionally followed by contrast normalization and max-pooling and dropouts to address the problem of overfitting
3. Followed by one or more fully connected layers at the end

Variants of this design were prevalent in…

Which three concepts lie at the heart of deep learning? — Loss Functions, Optimization algorithms, and Backpropagation. Without them, we would have been conceptually stuck at the perceptron model of the 1950s.

If you are completely unfamiliar with these terms, feel free to go through CS231n Lecture Notes 1, 2

If you want to learn about AlexNet, check out this blog where I have extensively covered it


Here is an example notebook, in which I have imported a pre-trained AlexNet model from PyTorch Library and used it for classifying an image.

Feel free to play around and discuss.


If you want to explore a bit more on AlexNet, go through my blog on ZFNet.


Although it was an updated version of AlexNet, the paper contributed towards our in-depth understanding of CNN architectures.

Originally published at on August 5, 2020.

VGGNet Architecture

Each year ILSVRC winners conveyed some interesting insights and 2014 was special in that regard. For most years the challenge tasks were:

  • Image classification: Predict the classes of objects present in an image.
  • Single-object localization: Image classification + draw a bounding box around one example of each object present.
  • Object…
ZFNet Architecture

ZFNet was introduced in the paper titled Visualizing and Understanding Convolutional Networks by Matthew D. Zeiler and Rob Fergus. This architecture did not win the competition, but its inference was implemented by the winner of that year ( Clarifai founded by Zeiler, 11.19% test error). This paper is remarkable because…

AlexNet Architecture (Split into two GPUs)

AlexNet was introduced in the paper, titled ImageNet Classification with Deep Convolutional Networks, by Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton and since then it has been cited around 67000 times and is widely considered as one of the most influential papers published in the field of computer vision. …

Zoheb Abai

Words change depending on who speaks them; there is no cure.

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