I am an Undergraduate student at RV College of Engineering , Bangalore studying Electrical and Electronics Engineering and expect to graduate in 2020. I am currently working in Ederlabs on privacy preserving Machine learning (PPML).

A proficient programmer in Java , Python and Javascript.

My interests are in Machine Learning , Privacy Preserving Machine Learning (PPML) and Software Engineering.

In PPML , I am specifically interested in Differential Privacy , Federated Learning and Trusted Execution Environments (TEE’s).

Available on Twitter as kamathhrishi and on LinkedIn.

Experience

Intern , Ederlabs (January 2020-Present)

Currently working on Differential Privacy.
Worked on privacy preserving machine learning using Trusted Execution Environment(TEE) Intel SGX.

Freelance Web Developer (July-October 2018)

Worked on two frontend projects for two clients using AngularJS and Bootstrap4.

Open Source Contributions

PySyft

“A library for answering questions using data you cannot see”
A framework for privacy-preserving deep learning using Pytorch and Tensorflow.
I worked on Pytorch development. Part of the Core team Contributed to Core PySyft Team

The experience helped me learn a lot of software engineering practices such as unit tests, code reviews, Git, writing clean and documented code.

• Wrote use cases of Federated Learning for developing Word Embeddings from Private Data and demonstration on CIFAR10
• Wrote an implementation of Differential Privacy method Private Aggregation of Teacher Ensembles (PATE)
• Tried working on Polynomial Tensor for non-linear computation in multiparty computation (MPC) setting. The method approximated non-linear computation using interpolation/Taylor series methods. Could not integrate it as part of Syft chain of tensors.
• Refactored data loaders and federated dataset and wrote a tutorial on developing custom federated datasets
• Type annotated the codebase and wrote documentation for parts of it

Deepgaze

Computer Vision library for human-computer interaction in Python

I have refactored certain parts of the library for improved usability and wrote test cases to ensure accurate functionality. Ported library to Python 3.0.

Some Projects I am proud of

For complete list of projects feel free to check my Github Profile.

Indoor Scene Recognition

• Trained a 8 layer Convolutional neural network (CNN) from scratch using Pytorch in Python to recognize 67 different indoor scene categories from just 5400 images.
• Read classical “CNN for Computer Vision” papers and explored various architectures.

Exploratory Analysis of Amazon Unlocked Mobile Reviews
Analyzed a dataset of 400,000 reviews for relationship between brands ,pricing and ratings using Seaborn and Pandas in Python.

Animals with Attributes
Supervised Learning

• Trained a 30 layer Residual CNN from scratch which could predict 50 different species of animals with 72% accuracy
• Finetuned a ImageNet pretrained 18 layer network to attain 89% accuracy

Zero Shot Learning

• Currently exploring Zero shot learning on the dataset. A naive implementation with Direct Attribute prediction attains 35% accuracy prediction unseen classes.

Contact

Contact me on kamathhrishi [at] gmail