AI Trends
Reporting, analysis and features from AIM's AI Trends section.
Top 10 open-source Responsible AI toolkits
TensorFlow Federated (TFF) is an open-source framework for decentralised machine learning.
sri.krishna ·
Real-time information extraction from documents with docTR
OCR is a short form of Optical character recognition or optical character reader. By the full form, we can understand it is something that can read content present in the image. Every image in the world contains any kind of object in it an…
Yugesh Verma ·
7 TED talks every AI enthusiast should watch
In this TED Talk, Dean answers the question- what is AI, really?
Avi Gopani ·
How to evaluate recommender systems fairly with RexMex?
Recommender systems help individuals in excluding the overwhelming choices of our daily lives. However, while such systems learn patterns from historical data, they can capture the bias mediated by the underlying data about imbalances and…
Sourabh Mehta ·
7 Github Repositories to Crack Tech Interviews in 2025
The Technical Interview Handbook covers technical and non-technical aspects of cracking a tech interview.
Pritam Bordoloi ·
How to generate images from text using DALL.E Mini?
Generating images from text method works by combining the observed and unobserved categories of text descriptions through some types of auxiliary information, which encodes observable distinguishing properties of objects.
Sourabh Mehta ·
Top open source datasets from Amazon
Over the years, Amazon and AWS have contributed massively to the open-source community by releasing their comprehensive datasets to the public.
Shraddha Goled ·
How can Queueing Theory be used in machine learning?
The Queuing Theory focuses on understanding how lines, or queues, work and how to increase their efficiency. It uses the knowledge of probability theory to calculate the different stages of the process.
Sourabh Mehta ·
Make a career in Data Science and AI with MTech from SRM Institute of Science and Technology
The program will take place during the weekends, and classes will be held at the Chennai Main campus, Kattankulathur.
Sreejani Bhattacharyya ·
7 outstanding papers at ICLR 2022
Sreejani Bhattacharyya ·
Top 5 Feature Stores from leading tech firms
Just a few days back, LinkedIn open sourced Feathr.
Sreejani Bhattacharyya ·
Optimizing search in high-dimensional data with Approximate Nearest Neighbours
In the approximate nearest neighbour, we take an approximate distance from the query point and classify the data point under the query.
Sourabh Mehta ·
Top basic Python hacks all programmers must know
The trimming hack is useful for scraping unwanted data.
Avi Gopani ·
Top 8 research papers by DeepMind in 2022 (till date)
Deepmind has published 34 research papers in the last four months.
kartik.wali ·
All you need to know about Markov Chain Monte Carlo
Markov Chain Monte Carlo (MCMC) refers to a class of methods for sampling from a probability distribution to construct the most likely distribution. Logistic distribution cannot be directly calculated, so instead generates thousands of val…
Sourabh Mehta ·
How to model uncertainty with Dempster-Shafer's theory?
One of the main advantages of Dempster-Shafer theory is that we can utilize it for generating a degree of belief by taking all the evidence into account
Yugesh Verma ·
Bayesian data analysis and visualization with ParaMonte
The Bayesian approach is used to analyze the data and update the beliefs based on data. Monte Carlo Markov Chain is a method that stimulates high dimensional probability distribution for Bayesian inference.
Sourabh Mehta ·
Top 10 tips to ace ML hackathons
TAIKAI claimed 40% of their hackathon participants were hired by companies in a matter of months.
kartik.wali ·
Implementing all decision tree algorithms with one framework - ChefBoost
ChefBoost is one python package that provides functions for implementing all the regular types of decision trees and advanced techniques. One thing which is noticeable about the package is we can build any version of the above-given decisi…
Yugesh Verma ·
How to make text classification explainable with the SS3 classifier?
SS3 has obtained state-of-the-art performance on the early risk detection (ERD) problems on text streams. Since it was designed to deal with risk detection over text streams, it supports incremental training and classification, as well as…
Sourabh Mehta ·