- Find a mentor
- Web Programming
- Mobile App Programming
- Programming Languages
- Data Science /Engineering
- Database /Operations
- Find a freelancer
GSOC '16, Deep Learning @ Pitney Bowes
Sessions / Jobs
For every 15 minutes
I am currently working as a deep learning engineer at Predible Health, Bangalore. We are using deep learning and cloud computation to deliver radiology reporting on web browsers. My specialties are building deep learning pipelines, scientific computing and building high performance python libraries.
- 3 years experience
For me Python is the way of living. I've been using it since I started programming. Most of my projects are built solely with Python. My Github is weaved around Python language, you are encouraged to take a look: https://github.com/simmimourya1. My experience is quite diverse. From Scientific computing, High performance computing, Data Science applications, Deep Learning applications, I've used Python for all of these. Nowadays, most of my time includes working with Deep Learning Frameworks built around python like Pytorch, Caffe 2, Keras.
- 1 year experience
I have a good experience of a lot of machine learning projects. I have been a part of 2 kaggle submission teams. One of my major submission was for LUNA 2016, https://luna16.grand-challenge.org/. It is a Lung Nodule Analysis Challenge. Some of the major algorithms that I've used are XGBoost for nodule spiculation classification, ARIMA for time series forcasting etc.
- 2 years experience
I've been working with Cython since past two years. My major contributions go to Cyvlfeat library, which is a high performance Cython/Python wrapper around VLfeat computer vision library. Please find the project here: https://github.com/simmimourya1/cyvlfeat See the contributor network: https://github.com/menpo/cyvlfeat/network I have presented talks at various international conferences including Europython Italy 2017, Pycon India 2017, FOSSASIA Tech Summit Singapore 2017. Find links below: https://ep2017.europython.eu/conference/talks/scientific-computing-using-cython-best-of-both-worlds https://in.pycon.org/cfp/2017/proposals/scientific-computing-using-cython-best-of-both-worlds~aO5Qd https://2017.fossasia.org/tracks.html#2956
- 2 years experience
I am currently working as a deep learning engineer at Predible Health, Bangalore. We are using deep learning and cloud computation to deliver radiology reporting on web browsers. Focus areas: Developing data driven fully automated deep learning engines to detect Lung Cancer and other related diagnostic features from Computed Tomography scans. I am working using Deep Learning in my projects since past two years. I have a strong background in Deep Learning and Machine Learning. I have completed Artificial Intelligence nanodegree from Udacity. I have given some Deep Learning workshops at my university as well. I am pretty good with Deep learning frameworks like Pytorch, Caffe 2 and Keras. I am also quite comfortable with Python scientific stack: Numpy, Scipy, Scikit-learn, Skimage, Matplotlb etc.
Diagonal Sudoku Solver and Isolation solver
Diagonal Sudoku Solver: Implemented two extensions of our sudoku solver. The first one to implement the technique called "naked twins". The second one to to solve a diagonal sudoku. Game playing agent for Isolation: Developd an adversarial search agent to play the game "Isolation". Isolation is a deterministic, two-player game of perfect information in which the players alternate turns moving a single piece from one cell to another on a board. Whenever either player occupies a cell, that cell becomes blocked for the remainder of the game. The first player with no remaining legal moves loses, and the opponent is declared the winner. These rules are implemented in the isolation.Board class provided in the repository.
Client: Udacity AI nanodegree
HMM based Sign Language Recognition System
Built a system that can recognize words communicated using the American Sign Language (ASL). By using a dataset of tracked hand and nose positions extracted from videos, I trained a set of Hidden Markov Models (HMMs) to try and identify individual words from test sequences. Incorporate Statistical Language Models (SLMs) that capture the conditional probability of particular sequences of words occurring. This helped me to improve the recognition accuracy of the system.
Client: Udacity AI nanodegree
Facial KeyPoint Detector and Dog breed classifier
Facial Keypoint detector: Built an end-to-end facial keypoint recognition system. Facial keypoints include points around the eyes, nose, and mouth on any face and are used in many applications, from facial tracking to emotion recognition. The pipeline takes in any image containing faces and identifies the location of each face and their facial keypoints Dog breed classifier: Built a pipeline to process real-world, user-supplied images. Given an image of a dog, the algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the algorithm will identify the resembling dog breed.
Client: Udacity Nanodegree
slides for my presentation
All basic algorithms.
POSTS BY SIMMI
Debug VLfeat’s Mex files in Visual Studio Community 2013 edition and Matlab release 2013a
It is highly recommended to go through this tutorial (http://in.mathworks.com/help/matlab/matlab_external/debugging-on-microsoft-windows-platforms.html?requestedDomain=in.mathworks.com) once. If...
Could've been better
Highly recommend! She is very knowledgeable about deep learning and has a superb organisation skill. You will be satisfied with the result.
Jan 11, 2018