Ayesha Siddiqua

*** * ********** **, *** # **,

Stillwater, Oklahoma, OK 74075

Email: adbtuh@r.postjobfree.com

Cell # 405-***-****

Summary

5+ years of experience in developing machine learning algorithms in MATLAB & Python.

Experienced in deep learning framework Caffe, Theano, Tensorflow and Torch

Developed and applied machine learning and deep learning including autoencoder and CNN for computer vision, imaging algorithms, speech etc. applications

Applied classification techniques using supervised/unsupervised learning and automated feature generation for depth image-based 3D model retrieval

Utilized GPU/Parallel architectures for algorithms. GPU programming languages, APIs

Used advanced analytics methods such as machine learning, advanced statistics, optimization, and estimation

Work Authorization

Legally authorized to work anywhere in the United States (Permanent Resident) Education Ph.D. in Computer & Electrical Engineering (GPA: 3.65/4.0) Oklahoma State University, USA.

2012-2019

M.S. in Computer & Electrical Engineering (GPA: 3.63/4.0) Oklahoma State University, USA.

2009-2011

B.S. in Computer Science & Engineering (GPA: 3.63/4.0) Shahjalal University of science and Technology, Sylhet, Bangladesh. 2001-2006

Professional Experience Research Assistant (Visual Computing & Image Processing Lab, OSU) January 2010- December 2018

● Deep Learning Research: Supervised deep autoencoder for retrieving relevant 3D models based on depth images of NYUD2 dataset.

Worked with two different domain datasets, NYU Depth image version2 & ModelNet10

Dealt with 59382 training depth images for 10 categories using deep network

Challenges: Incomplete and occluded dataset

Developed a deep learning algorithm: Supervised deep autoencoder for depth image based 3D model retrieval published in WACV 2018

Deep learning framework: Python, Caffe and MATLAB

Current deep learning research: Supervised deep autoencoder followed by semantic modeling for depth image-based 3D model retrieval.

● Deep Learning Projects:

Object Classification from NYUD2 depth image using deep autoencoder feature & Convolutional Neural Network (CNN), in Python and caffe platform.

Applied Multi Layer Perceptron network on MNIST dataset and analyzed the network performance for different batch size, number of layers, number of neurons and optimization functions. (Lua & Torch, python & caffe)

Applied & analyzed LSTM network and recurrent network for predicting the next word after a sequence of words (Python & Tensorflow )

● Machine Learning Research (M.S. Thesis): Advanced Machine learning approaches and optimization for estimation of Center of Mass from unknown human motion. o Developed a Probabilistic algorithm (Gaussian Process Regression) & a Supervised Manifold Model algorithm (Torus).

● Data Science, Machine Learning and Data Engineering Projects: o Data Analyzing: Profitable App Profiles for the App Store and Google Play Markets Predicting Modeling: Clustering and segmentation using PCA/ KNN/autoencoder

(segmented customers of an online retail business), Logistic regression(predicted house sale prices), Linear regression (predicted stock market), Decision tree(predicted bike rentals), Random forest(forecasted seattle weather), Classification using XGBoost (customer lifetime value prediction, churn prediction, customer retention model), LSTM network (sales prediction), Semantic modeling, Deep autoencoder, Convolution Neural Network (Classified depth images/handwritten digits), SVM

o Probability and Statistics: Investigating Fandango Movie Ratings, Finding the Best Markets to Advertise In

o Data Engineering: Designed and implemented data warehouse and cleaned up the data for US flights 2002 using PostgreSQL & python.

o Natural Language Processing: Tweet Visualization and Sentiment Analysis in Python Lecturer, Premier University, Computer Science, Chittagong, Bangladesh 2007- July 2008 Relevant Courses_ _ Deep Learning, Computer Vision, Pattern Recognition, Neural Networks, Stochastic Systems, Principles of database, Distributed database system, Data structure and algorithm Technical Skills_ _

•Programming languages: Python, Matlab, C, Java, SQL, MySQL, postgresql, java, Oracle, PHP, R

•Deep learning tool: Caffe, Theano, Tensorflow, Torch, Lua.

•Big Data & visualization tools: Python, numpy, Scikit Learn, Panda, Matplotlib, Seaborn, Scipy, nltk

•Platform & Cloud: Git, Jupyter, Windows, Linux, Azure, AWS Scholarships _

• Graduate Fellowship from the School of Computer Science & Electrical Engg., Oklahoma State University, since Aug. 2008.

• Lynn T Miller Scholarship, College of Engineering, Architecture & Technology, OSU, 2013-2016.

• Women’s Faculty Council Student Research Award, OSU, 2018 References __ Available on request.