You don’t always need a lot of data to train your model, learn how to create a model with a tiny number of images per class

Photo by Lisa Algra on Unsplash

In the modern Deep learning era, Neural networks are almost good at every task, but these neural networks rely on more data to perform well. But, for certain problems like face recognition and signature verification, we can’t always rely on getting more data, to solve this kind of tasks we have a new type of neural network architecture called Siamese Networks.

It uses only a few numbers of images to get better predictions. The ability to learn from very little data made Siamese networks more popular in recent years. …

Machine Learning

Photo by Mohamed Nohassi on Unsplash

Motivated by prior work connecting the geometry of the loss landscape
and generalization, we introduce a novel, effective procedure for instead simulta- neously minimizing loss value and loss sharpness. In particular, our procedure,
Sharpness-Aware Minimization (SAM), seeks parameters that lie in neighbor-
hoods having uniformly low loss; this formulation results in a min-max optimiza- tion problem on which gradient descent can be performed efficiently. We present empirical results showing that SAM improves model generalization across a variety of benchmark datasets[1]

Source: Sharpness Awareness Minimization Paper [1]

In Deep Learning we use optimization algorithms such as SGD/Adam to achieve convergence in…


In this article we will learn about itertools module and how to use them, It is one of the standard modules in Python which works on top of standard iterators.

What are iterators?

From Wikipedia[1],

In computer programming, an iterator is an object that enables a programmer to traverse a container particularly lists

In simple words, an iterator is a certain object that helps us to loop over a certain data structure such as lists, dictionary, etc..and gives access to the elements on those datastructures.

Thus, itertools module contains functions that operate on iterators to produce complex iterators

What are Itertools?

From the documentation[2],

This module…

From Lenet to ResNet

Photo by James Padolsey on Unsplash

Convolutional Neural networks are a class of Deep Neural Networks, which achieve State of the Art results not only in Computer Vision tasks but also in other fields such as Speech recognition, Natural Language Processing, etc. These CNNs have evolved in a long way by not only stacking layers but also creating custom layers. In the current world, we use these models to transfer learning and achieve better results.

In this article, I will write how to implement state of the art CNN architectures from scratch in Pytorch. I assume that you know the theory about these CNNs, so that…

Photo by Scott Graham on Unsplash

Coronavirus didn’t bother me a lot, but due to a pandemic when the whole world started to shut down, it does panic me a lot!, Like every other CS student, I decided to learn some skill within the Quarantine and apply it to solve real-world problems

Now(even though quarantine didn’t end), I write this article to share my experience how learning Machine Learning and Data Science helped me (and will help you!) to become more productive than ever, also how you can also start learning Machine Learning and Data Science

Why Machine Learning?

For the sake of getting a better, highly paid job…

Sean Benhur J

ML Practitioner | Applied Math | Find me here

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