Sowmya-Iyer

BayesianAdversarialDefense

Estimating the robustness of Baysian models towards Gradient-based Adversarial attacks

Blood-Vessel-Segmentation-in-fundus-images-for-Diabetic-Retinopathy

We propose LadderNet, a convolutional network for semantic segmentation with more paths for information flow. We demonstrate that LadderNet can be viewed as an ensemble of FCNs, and validate its superior performance on blood vessel segmentation task in retinal images.

COGNITIVE-AI-LED-CATEGORIZATION-OF-DRIVER-STOPS-APPLICATION

Unsupervised learning was leveraged on data (electric vehicle (two-wheeler) with GPS location fired every few seconds of delivery agents of a company) to analyze and categorize stops as hubs, driver location, illegal stops and delivery locations by clustering and reinforced it with location description extracted using Google Places APls

HMC-for-Gaussian-Mixture-Model-parameters

GMM descibes a set of points in the 2D plane. Implemented a posterior sampler using the Hamiltion Monte Carlo (HMC) algorithm.

ISL2MoCap

Using supervised learning, ISL Mocap dataset is built and rendered in blender

ML-for-Beginners

Quick implementation of ML Concepts

Multimodal-transformers

OpenCV-Mini-Projects

OpenCV

T5-transformer-for-title-generation

Web-Scraping-Coursera-courses

Sowmya-Iyer/Web-Scraping-Coursera-courses

Sowmya-Iyer/HMC-for-Gaussian-Mixture-Model-parameters

GMM descibes a set of points in the 2D plane. Implemented a posterior sampler using the Hamiltion Monte Carlo (HMC) algorithm.

Sowmya-Iyer/BayesianAdversarialDefense

Estimating the robustness of Baysian models towards Gradient-based Adversarial attacks

Sowmya-Iyer/Blood-Vessel-Segmentation-in-fundus-images-for-Diabetic-Retinopathy

We propose LadderNet, a convolutional network for semantic segmentation with more paths for information flow. We demonstrate that LadderNet can be viewed as an ensemble of FCNs, and validate its superior performance on blood vessel segmentation task in retinal images.

Sowmya-Iyer/COGNITIVE-AI-LED-CATEGORIZATION-OF-DRIVER-STOPS-APPLICATION

Unsupervised learning was leveraged on data (electric vehicle (two-wheeler) with GPS location fired every few seconds of delivery agents of a company) to analyze and categorize stops as hubs, driver location, illegal stops and delivery locations by clustering and reinforced it with location description extracted using Google Places APls

Sowmya-Iyer/ISL2MoCap

Using supervised learning, ISL Mocap dataset is built and rendered in blender

Sowmya-Iyer/ML-for-Beginners

Quick implementation of ML Concepts

Sowmya-Iyer/Multimodal-transformers

Sowmya-Iyer/OpenCV-Mini-Projects

OpenCV

Sowmya-Iyer/Scrape-Youtube-Video-Python-

save youtube videos in a local file and also convert them into a gif

Sowmya-Iyer/Sowmya-Iyer

Sowmya-Iyer/T5-transformer-for-title-generation

Sowmya-Iyer/abc-to-midi-

for Music Generation

Sowmya-Iyer/Adaptive-Learning-rate-and-regularization-from-scratch-using-Pytorch

Adaptive Learning rates: Momentum, Nesterov Momentum, and Adam; Regularization: L2

Sowmya-Iyer/Binary-sentiment-classification

Implemented Perceptron and Logistic Regression and compared their performance on the sentiment classification task

Sowmya-Iyer/CareerQuest.in

In Progress

Sowmya-Iyer/Deploy-WordPress-to-a-non-window-Instance

Sowmya-Iyer/Disaster-Tweet-Classification

Sowmya-Iyer/Edge-Detection-using-OpenCV

Sowmya-Iyer/Fruit-image-classifier

Building a CNN from scratch

Sowmya-Iyer/Image-classification-on-CIFAR-10

Sowmya-Iyer/Kaggle

Sowmya-Iyer/Leetcode-solutions

Sharing my leetcode submissions for reference

Sowmya-Iyer/MargSetu

Machine Learning powered Web Application to recommend you Massive Open Online Courses (MOOC) from Coursera 💙⚡

Sowmya-Iyer/MocapNET

We present MocapNET, an ensemble of SNN encoders that estimates the 3D human body pose based on 2D joint estimations extracted from monocular RGB images. MocapNET provides BVH file output which can be rendered in real-time or imported without any additional processing in most popular 3D animation software. The proposed architecture achieves 3D human pose estimations at state of the art rates of 400Hz using only CPU processing.

Sowmya-Iyer/QoS-Class-Label-Based-Network-Traffic-Classification

Sowmya-Iyer/Reading-a-.db-file-using-Python-sqlite3

Sowmya-Iyer/Sowmya-Iyer.github.io

Sowmya-Iyer/system-monitoring-app

Built using Python and Flask with cloud demonstrations and containers in mind

Sowmya-Iyer/Technical-Documents