- Currently working with multi-modal transformers
- Pursuing Masters in Computer Science at Purdue
- 📝 My Resume
Name: Sowmya J Iyer
Type: User
Bio: Deep Learning | Computer Vision | Machine Learning
Location: West Lafayette
for Music Generation
Adaptive Learning rates: Momentum, Nesterov Momentum, and Adam; Regularization: L2
Ways to approach data before deciding on a model for csv and image data as well
Estimating the robustness of Baysian models towards Gradient-based Adversarial attacks
Implemented Perceptron and Logistic Regression and compared their performance on the sentiment classification task
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.
In Progress
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
Notes and experiments to understand deep learning concepts
Building a CNN from scratch
GMM descibes a set of points in the 2D plane. Implemented a posterior sampler using the Hamiltion Monte Carlo (HMC) algorithm.
Using supervised learning, ISL Mocap dataset is built and rendered in blender
Sharing my leetcode submissions for reference
Machine Learning powered Web Application to recommend you Massive Open Online Courses (MOOC) from Coursera 💙⚡
Quick implementation of ML Concepts
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.
Looking beyond the images
OpenCV
save youtube videos in a local file and also convert them into a gif
My Portfolio Site | Made With @Gatsbyjs
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.