MOHIT NIHALANI

*** ******* ******, ****** ****, NJ . adbqvj@r.postjobfree.com . 917-***-****

Education

New York University, Courant Institute of Mathematical Sciences 2019-2021 MS Computer Science

Relevant Courses: NLP, Big Data, Advanced Algorithms, Cognitive Computing University of Surrey, Guildford, United Kingdom 2015-2018 BSc. (Hons) Computer Science Result: First class – 76.75% Relevant Courses: Computational Intelligence, Computer Security, Deep Learning and Advanced AI, parallel computing. Imperial College Business School, London 2017

The Entrepreneurial Smart Camp (Summer Course)

Work Experience

Data Artist Intern, Pykih, New Delhi, India Nov 2018- June 2019

• Collaborated with TheHindu to create a visualization model to study changes in Indian constitution, which received more than 100 thousand visits in a single month, comprised mostly of Journalist and Law, Politics and UPSC students.

• Worked with OpAsha (NGO), to design an NP-Hard algorithm which allocates Health community workers efficiently. K-means clustering and DBSCAN method were used for regional clustering and to find optimal centroids for each cluster(worker).

• Designed and implemented Tableau dashboards for clients that help them to measure the performance of subscribers in different regions of India.

• Optimized company’s database storage model, which reduced latency and improved CRUD performance by more than 50%. Teaching Assistant & Grader, University of Surrey, United Kingdom Sep 2017-June 2018

• Mentored junior computing students (around 100) through lab sessions and recitation classes. Modules includes Object oriented programming, Advance Algorithms, Information Retrieval, Parallel Computing and Computer Networking.

• Conducted office hours for students requiring additional assistance. Selected Projects and Coursework’s

• Machine Learning: Presented detailed analysis of the effects of parameters on the CNN and SVM models for image classification and proposed an Ensemble-Hybrid model which obtained classification accuracy of 94.6% on CIFAR-10 dataset and optimized the hyper parameters using adaptive genetic algorithms.

• Deep Learning: Build a CNN and LSTM hybrid model to predict Individual household electric power consumption. Model was trained using measurements of electric power consumption with a one-minute sampling rate over 4 years. The project was acknowledged as the best LSTM model use in the class.

• Android App: Designed mobile app for dementia patients. It provides features such as tracking medication and medical appointments, creates a family tree by exporting images from gallery, identifying nearby pharmacies and service providers, emergency button and offering cognitive learning games to test knowledge and memory.

• Evolutionary Algorithm: Used binary coded genetic algorithms to optimize the weights of neural network. Used two different learning methods Rprop and Rprop+ which were embedded with two different learning mechanism; Baldwinian and Lamarckian.

• Other Projects:

AI: Handwriting and signature recognition system using neural networks; movie recommendation system using Restricted Boltzmann Machine and stacked autoencoders.

Developed VR games such as “Whack mole art”, “Ninja Sword”, “Space Shooter”.

Implemented Affine Vigenere Cryptosystem.

Morse code decoder on Arduino board.

Achievements

• Earned STARS (Surreys Top Achievers Recognized and supported) for two consecutive years.

• Voted as the best TA by undergraduate computer science students. Technical Skills

• Programming Languages: Experience in Java, Python, R, C++

• Web Technologies: HTML, CSS, react, node.js, next.js

• Machine Learning/AI: TensorFlow, Keras, Scikit, Theano, Shark, PyTorch

• Database: Mongo db, SQL, HBase, Impala

• Frameworks: Ruby on Rails, Express.js, Hadoop, Spark

Contact this candidate