Deep Tech
Reporting, analysis and features from AIM's Deep Tech section.
A beginner’s guide to Bayesian CNN
Applying bayesian on neural networks is a method of controlling overfitting. We can also apply bayesian on CNN to reduce the overfitting and we can call CNN with applied Bayesian as a BayesianCNN.
Yugesh Verma ·
Contrastive vs non-Contrastive Self-Supervised Learning Techniques
On the contrary, to collapse in contrastive methods, FAIR identified non-contrastive methods to suffer from a lesser collapse problem of a different nature.
Avi Gopani ·
A beginner's guide to text regression with AutoKeras
We can think of text regression as a method of using attributes from the text data as a covariate in regression models. There are various fields where we may require regression analysis methods such as predicting salary based on the text w…
Yugesh Verma ·
A guide to Orchest for building ML pipelines
Orchest is a tool that can be utilized for building machine learning pipelines. Using this library we can build pipelines in a visualized manner using the Orchest provided user interface. One of the best things about this tool is it doesn'…
Yugesh Verma ·
NVIDIA GTC 2022: What we predicted vs what actually happened
NVIDIA H100 will be the engine of the world's AI infrastructure that enterprises will use to accelerate their AI-driven businesses, said Jensen Huang.
Sreejani Bhattacharyya ·
Transfer learning vs federated learning: A comparative analysis
Federated learning enables smarter models, lower latency, and less power consumption, all while ensuring privacy.
Sreejani Bhattacharyya ·
A guide to image illumination editing with OpenCV
In digital image processing, a lot of various methods are used to increase the quality of the image such as noise reduction, high resolution, etc. Image illumination is one such technique that highly affects the quality of the photo.
waqqas.Ansari ·
A beginner’s Guide to Bayesian Additive Regression Trees
BART stands for Bayesian Additive Regression Trees. It is a Bayesian approach to nonparametric function estimation using regression trees.
Sourabh Mehta ·
A hands-on guide to time series modelling pipelines using EvalML
EvalMl is a python library for automated machine learning that helps us in building, optimizing, and evaluating machine learning pipelines.
Yugesh Verma ·
A beginner’s guide to Video and Language Pre-training models (VL-PTMs)
With the recent advances of self-supervised learning, pre-training techniques play a vital role in learning visual and language representation.
Sourabh Mehta ·
A guide to CoAtNet: The combination of convolution and attention networks
CoAtNets is a hybrid model built by Google's Brain Team and has recently gained the attention of deep learning practitioners.
waqqas.Ansari ·
Major announcements made by Jensen Huang at NVIDIA GTC 2022
NVIDIA GTC 2022 began on March 21 and will continue till March 24. One of the highlights of the event was CEO Jensen Huang’s keynote address.
Shraddha Goled ·
Masterclass on AI innovation with oneAPI by Intel
This session is curated to help developers with basic knowledge of C or C++ and GPU programming.
Amit Naik ·
A guide to XAutoML: A tool for visual analytics
XAutoML is an analytics tool that explains the AutoML optimization procedures and machine learning pipelines constructed by AutoML.
waqqas.Ansari ·
A guide to different image reconstruction techniques for beginners
In this article, we will go through an overview of each of the popular image reconstruction techniques and will understand how these techniques work.
waqqas.Ansari ·
Interview with the team behind Microsoft’s µTransfer
Recently, researchers – Edward Hu, Greg Yang, Jianfeng Gao from Microsoft, introduced µ-Parametrization, which offers maximal feature learning even in infinite-width limit.
Shraddha Goled ·
Difference Between Zero-shot, One-shot and Few-shot Learning?
Zero-shot learning has found application in critical areas like healthcare for medical imaging and COVID-19 diagnosis using chest x-rays as well as for unknown object detection used in autonomous vehicles.
poulomi.chatterjee ·
A guide to explaining feature importance in neural networks using SHAP
SHAP values (SHapley Additive exPlanations) is an awesome tool to understand your complex Neural network models and other machine learning models such as Decision trees, Random forest.
waqqas.Ansari ·
A guide to parallel deep learning with Colossal-AI
Colossal-AI is such a powerful system that can perform complicated distributed training and give an easy way to set up different types of parallelism.
waqqas.Ansari ·
How Tesla’s self-driving technology compares to other EVs
While the Mercedes could only drive itself on the freeway, Tesla’s vehicle can work anywhere.
poulomi.chatterjee ·