Education

Ph.D in Electrical and Computer Engineering

University of Iowa, Iowa City, USA

B.Sc. in Electronics and Telecommunication Engineering

Chittagong University of Engineering and Technology, Chattogram, BD

Higher Secondary Level

Ispahani Public School and College, Cumilla, BD

Secondary School Level

Ispahani Public School and College, Cumilla, BD

ECE 5460 Digital Signal Processing

UIowa

• Learning Outcomes
  • Got familiar with DTFT, z-transform and causality and stability analysis of system.
  • Learnt about Type I-IV filters, All pass and Minimum phase systems.
  • In-progress

ECE 5600 Control Theory

UIowa

• Learning Outcomes
  • Learnt about the SISO and MIMO systems
  • Learnt about state variable representation of system, stability analysis using transfer function.
  • In-progress

ECE 5995 Large Language Models

UIowa

• Learning Outcomes
  • Learnt about the small language models and the concept for textual feature extraction such as n-grams, bag-of-words etc.
  • Learnt about the architectures of the Transformer model.
  • Learnt about various state-of-the art LLMs such as - GPT, RoBERTa etc.
  • Got familiar with LoRA and other techniques.

ECE 5995 Intelligent Vision and Image Understanding

UIowa

• Learning Outcomes
  • Learnt about various image enhancement and filtering techniques.
  • Learnt about various edge, corner detection and line detection algorithms.
  • Learnt about conventional and AI-based approaches for image segmentation.
  • Got familiar with image registration, mathematical morphology, wavelet theory

ECE 5320 High Performance Computer Architecture

UIowa

• Learning Outcomes
  • Got familiar with the quantitative measures for assessing and comparing processor performance.
  • Learnt about various processor design techniques, including - pipelining, instruction level parallelism, out-of-order execution, speculative execution, memory architecture, multi-threading, GPU architecture etc.
  • Used simulations to design and analyze processors.
  • Learnt about the future trends of processor design.

ECE 5450 Machine Learning

UIowa

• Learning Outcomes
  • Gained an in-depth understanding of machine learning theory & algorithms.
  • Learnt about curve fitting, constrained optimization and Lagrange multipliers method, least squares, bias vs variance tradeoffs, MLE, MAP, SVM, K-means clustering, Mixture of Gaussians, EM algorithms for GMMs.
  • Implemented the algorithms in Python to get hands-on experience.

ECE 5470 Medical Imaging Physics

UIowa

• Learning Outcomes
  • Got familiar with the various imaging modalities.
  • Learnt about the principles and methods of acquiring imaging data.
  • Learnt about the physics and data acquisition technique of major medical imaging modalities (X-ray, CT, MRI, Ultra-Sound, PET, SPECT)
  • Learnt about the factors influencing image characteristics and image qualities in individual modalities.

BME 5240 Deep Learning in Medical Imaging

UIowa

• Learning Outcomes
  • Got familiar with image space and physical space.
  • Learnt about techniques to represent, reorient and standardize medical image.
  • Learnt to implement image processing pipeline using SimpleITK.
  • Got familiar with various NN architectures for tasks such as - classification, segmentation, registration and synthesis.
  • Got familiar with libraries such as - MONAI, PyTorch, SimpleITK

ECE 5820 Software Engineering Languages and Tools

UIowa

• Learning Outcomes
  • Got familiar with the various aspects of software engineering.
  • Got familiar with concepts such as - TDD, BDD, Agile & Waterfall methodologies.
  • Learnt about various tools such as git, github, kanban board.
  • Got hands on experience of working in a team and develop an web app following the industry practices such as - working as developer or product manager in the team, holding stand up meeting in every other day, getting out a minimum viable product in every sprint, writing tests and generating test coverage report etc.

MATH 4820 Optimization Techniques

UIowa

• Learning Outcomes
  • Learnt to identify conditions under which global minimizers exist.
  • Learnt to identify critical points and when a critical point is definitely a local minimizer.
  • Learnt to implement and use basic optimization algorithms such as gradient descent.
  • Got familiar with line searches for gradient descent.
  • Learnt about Newton method and variants for optimization.
  • Learnt about conjugate gradient method and quasi-Newton methods.
  • Learnt to formulate constrained optimization problems (equality and inequality constrained optimization).
  • Learnt about Lagrange multipliers, and Karush-Kuhn-Tucker conditions via Farkas lemma.
  • Learnt about stochastic methods for continuous optimization & stochastic differential equations, optimization with differential equations - optimal control.

ECE 5330 Graph Algorithm and Combinatorial Optimization

UIowa

• Learning Outcomes
  • Learnt about the basic data structures and algorithms.
  • Learnt to analyze algorithms - space and time complexity, big-Oh notation, recurrences.
  • Learnt about classic algorithm design techniques such as - divide and conquer, dynamic programming and greedy methods.
  • Learnt about basic graph algorithms (DFS, BFS, Toplolgical sort) - graph traversal techniques, shortest path algorithms and minimum spanning trees.
  • Learnt about network flows (Ford-Fulkerson method, Push-relabel algorithms) - maximum flows, matching and graph cuts
  • Learnt about NP-Hard, NP-completeness and approximation algorithms.

ECE 5995 Applied Machine Learning

UIowa

• Learning Outcomes
  • Learnt about probability distributions, information theory, entropy
  • Learnt about linear and kernel regression and classification.
  • Learnt about neural network, optimization and regularization of neural networks.
  • Learnt about factor based generative models - PCA, kernel PCA and applications - Low-rank methods
  • Learnt about the generative models - Auto-encoder, Variational Auto-encoder, GANs and diffusion models and their relation to energy models.
  • Learnt about disentanglement of latent variables and tricks to improve representation power.

Learn to Code with Python

Udemy

View

• Learning Outcomes
  • Learned about data structures in python.
  • Learned python code debuggging and testing.
  • Got familiar with object oriented programming in python.
  • Learned to handle exceptions.
  • Got familiar with web scrapping and regular expressions.

AWS Machine Learning Fundamentals

Udacity

View

• Learning Outcomes
  • Learned about software engineering principles and how they apply in data science.
  • Got familiar with generative AI and AWS DeepComposer.

Complete Tensorflow 2 and Keras Deep Learning Bootcamp

Udemy

View

• Learning Outcomes
  • Learned about TensorFlow 2.0.
  • Learned to leverage Keras API to quickly build models.
  • Learned to apply deep learning in medical imaging.
  • Learned to build Generative Adversarial Networks (GNN).
  • Got familiar with Autoencoders.
  • Learned to deploy ML model.

Deep Learning Specialization

Coursera

View

• Learning Outcomes
  • Got fundamental knowledge of how neural networks (NNs) work.
  • Learned the mathematics working behind backpropagation, gradient descent algorithms etc.
  • Learned to tune hyperparameters of NNs.
  • Learned about model evaluation metrics
  • Got hands-on experience in building NNs.

Digital Signal Processing

Coursera

View

• Learning Outcomes
  • Learned about various signal properties.
  • Got familiar with various operations and transformation techniques in signal processing.

Machine Learning

Coursera

View

• Learning Outcomes
  • Gathered in an in-depth understanding of some supervised and unsupervised ML algorithms.
  • Learned the best practices in ML while studying a number of cases.

Fundamentals of Research Methodology

Scholarship School BD

View

• Learning Outcomes
  • Learned how to read research papers effectively.
  • Learned how to write research papers using LaTeX and MS Word.
  • Learned about finding research articles online.
  • Got hands-on experience in writing resarch paper using mendeley.

AI and Machine Learning in Python

Sheikh Kamal IT Business Incubator, CUET, BD

View

• Learning Outcomes
  • Got familiar with various NLP libraries e.g., nltk, GloVe, spacy etc.
  • Learned to code neural networks combining multiple modalities.

Foundations in Digital Forensics with Magnet Axiom

Sheikh Kamal IT Business Incubator, CUET, BD

View

• Learning Outcomes
  • Got familiar with Magnet Axiom.
  • Learned to perform digital forensics using Magnet Axiom.
  • Learned to prepare forensic report using Magnet Axiom.