Computer Vision is one of the hottest domain especially at times like these when a pandemic is nudging us towards vision solutions in different industries . Traditional Computer vision was based mainly on the image processing algorithms while Deep learning based CV provides an end to end solution to vision problems which exacerbated their applicability in much wider areas . Some applications which add value are dimensioning solutions , People tracking in surveillance, Autonomous driving

Now , all you Developers out there might or might not have been exposed to these approaches but we are going to discuss something which…


Treating abnormal events as a binary classification problem is not ideal for two reasons :

  1. Abnormal events are challenging to obtain due to their rarity.
  2. There is a massive variety of abnormal events, and manually detecting and labeling such events is a difficult task that requires much manpower.

A better approach would be to use unlabelled video sequences with little or no abnormal events to train which are obtained easily . Autoencoders require just that

The above flowchart explains the working of a trained ConvLSTM Autoencoder

  • Reconstructed clip is output by the Autoencoder
  • Based on the error (reconstruction cost) between…


The entire paper can be summarized in three stages :

Self-supervised learning → Clustering → Self labelling

Self supervised learning : (Mining K nearest neighbors)

A typical image classification task would involve labels to govern the features it learns through a Loss function . But when there are no labels to govern such backpropagation in a network how do we get the network to learn meaningful features from the images ?

Self — supervised representation learning involves the use of a predefined task/objective to make sure the network learns meaningful features . Let’s take a NN of 5 layers …


A story using GRE words (Group 2 : 30 words)

These groups are part of GregMat’s vocab list . You can check those out in the links below

https://docs.google.com/spreadsheets/d/1jRATLVV34vATsL4Y67fZZXQc7qZPYc0c0Yk7Bykh4fw/edit#gid=0

Children today are adulterated with unimportant tasks which they perceive as important . Experts advocate a change in parents behavior to automatically nudge them to decide which are actually important. Privileged kids are burdened with the responsibility of aggrandizing their parents’ reputation which eventually makes them lose the alacrity to do what they love . What happens in turn is their thoughts risk the nature of being ambivalent all the time…


A story using GRE words (Group 1 : 30 words)

These groups are part of GregMat’s vocab list . You can check those out in the links below

Here we go !

Thoughts abound when in solitude , thanks to COVID-19, some endearing some not so. A state which we considered order turned amorphous if not chaos . We have been forced into or gifted an austere life . A lot of questions being raised with belied responses . Each day with a capricious outcome, not many can handle . funny how a fear of a predictable outcome can result…


Correlation is the first step in finding relationships between quantities and deserves some attention . Correlation is defined as the association between quantities , for eg, the sales might increase when income of people increases

Before we dwell into the math , we need to understand Co-variance . Co-variance is the statistical measure of association between variables

Cov(x,y) = E [ (x — E[x]) (y — E[y]) ]

The equation above is equation for Co-variance , let’s break this down

E denotes the expected value of a variable , which is nothing but the mean . x — E[x] is…

Shyam Sundar

Machine Learning Engineer at e-con systems | Deep learning (Computer vision) | Great lakes PGP DSE

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