Home

Deep Learning

No one knows what the right algorithm is, but it gives us hope that if we can discover crude approximations of whatever this algorithm is and implement on a computer, that can help is make a lot of progress.- Andrew Ng
Computer Vision

Vision begins with the eyes, but truly takes place in the brain. Collectively, as a society, we are very much blind because our smartest machines are blind.-Fei Fei Li
Natural Language Processing

To strengthen the connection between your conscious and subconscious, is to gain access to a map and compass, as you travel through parallel worlds.
Welcome to the future.

Computers are able to see, hear and learn.

Pages overview

Meraki Hues-Art Work

By Mrunal Jadhav

About Us

Learn more about the authors of this blog or just say us Hello!!

Recent articles

Neural Machine Translation - French to English

Sun, 12 Jul 2020 by Pritish Jadhav, Mrunal Jadhav / Deep Learning, NLP

A sequence to sequence model lies behind numerous systems which we use on a daily basis. In this blog, we will try to give a short and concise explanation of the sequence to sequence model and apply it to achieve significant results on pretty complex tasks of machine translation.

Naive Bayes

Mon, 18 May 2020 by Mrunal Jadhav,Pritish Jadhav / Probability and Statistics

Naive Bayes belongs to the family of probabilistic algorithms that take advantage of Probability Theory and Bayes Theorem to predict the class. Let's learn how it works!!

Conditional Probability and Independence

Wed, 13 May 2020 by Mrunal Jadhav,Pritish Jadhav / Probability and Statistics

In supervised machine learning, we are building predictive models that predict variance of some variable, using variance of some other variables. To model these connections, we have to learn Conditional Probabilities and Independence of events.

Hierarchical Attention Network For Multilabel Classification (Detailed Case study)

Wed, 11 Sep 2019 by Pritish Jadhav, Mrunal Jadhav / Deep Learning

In many real-world data applications, often we encounter scenarios where each data point may belong to multiple classes. A multilabel classifier is trained to predict the K most likely classes among N possible classes. The article focuses on solving multi-label text classification problems using the Hierarchical Attention Network.