Hi I'm,
Mohd.Farhan Israk Soumik,
Researcher at AGenCy Lab, Independent University, Bangladesh Download Resume
About Me _______
Hello,I'm Mohd.Farhan Israk Soumik,graduated from Department of CSE of.Rajshahi University of Engineering & Technology in the year 2021. I am passionate about Machine Learning more particularly regarding the fields of Deep Learning. Also highly interested in Python and a backend developer working on Python and Django.
Contact MeEducation
Rajshahi University of Engineering & Technology(BUET)
B.Sc in Computer Science & Engineering(CSE)
(2016 - 2020)
Khulna Public College
Higher Secondary School Certificate, Science
Grade: 5.00 in the scale of 5.00
(2016 - 2020)
Experience
Research and Teaching Assistant
Jan 2022 - Present | Independent University, Bangladesh · Full-time
Research Assistant at Center For Computation and Data Science(CCDS) and Artificial intelligence and Cybernetics Lab(AGenCy Lab) at independent University, Bangladesh.
Data Science and Business Analytics Intern
Jul 2021 - Aug 2021 | The Sparks Foundation · Internship
In these tough times of COVID-19, businesses have been working towards creating a predictive model of everything possible. To speak about a few, where will our economy be in the next few quarters?
Projects
Blogger- A Social Networking Blogsite
Apr 2021 - Jun 2021
Social networking blogsite where registered users can post, comment, like and edit both post and comments. Here for backend Django has been extensively used and frontend has been developed using html, css and vanilla javascript. Backend: Django Frontend: html, css and javascript.
Creating Multi-Task Branched Deep Learning Model Using Tensorflow
May 2021 - May 2021
In this project, I have created and trained multi-task, multi-output models with Tensorflow and it's Keras API. Here, I have used Keras' functional API to create a multi output model which can be trained to learn two different labels given the same input example...
Muti Taksed Deep Learning Model For Object Localization
Apr 2021 - May 2021
In this project, I have used Multi-taksed deep convolutional neural network for at the same time classifying the object and localizing the object inside the image by plotting boundary boxes surrounding it. Dataset was generated by randomly positioning the...
Visualizing Layers of Deep Convolutional Neural Network
Apr 2021 - May 2021
While performing classification tasks using deep neural network based models what happens inside each layer or which layer impacts most on right/wrong classification or how different layer impact final decision making...
Fine Tuning BERT for Text Classification Using Tensorflow
Apr 2021 - Apr 2021
This is a project on fine-tuning a Bidirectional Transformers for Language Understanding (BERT) model for text classification with TensorFlow. In this long project, I had to preprocess and tokenize data for BERT classification...
Tweet Emotion Recognition with Tensorflow
Apr 2021 - Apr 2021
The structural organization of this project can be defined into following categories: 1) Using a Tokenizer in TensorFlow 2)Padding and Truncating Sequences 3) Creating and Training Recurrent Neural Networks 4)Using NLP and Deep Learning to perform Text...
Publications
Improved Transfer Learning Based Deep Learning Model For Breast Cancer Classification From Histopathological Images
IEEE · Jul 28, 2021
In recent years, the demand for prompt detection and classification of breast cancer is rising sharply as breast cancer has become leading cancer type among women throughout the world. ConvolutionalNeural Networks(CNNs) are widely being used for performing mentioned tasks.However, they need a large number of labeled images which may appear to be infeasible for some kinds of medical images data such as mammographic tumor images...
Brain Tumor Classification Using Inception Network Based Deep Learning Model Using Transfer Learning
IEEE · Nov 2, 2020
Abstract: Brain tumor classification is one of the most important aspects in the fields of medical image analysis. As tumors are regarded as precursor to cancers, efficient brain tumor classification can prove life saving. For this reason, Convolutional Neural Network(CNN) based approaches are widely being used for classifying brain tumors. However there lies a dilemma, CNNs are accustomed to large amount of training data for giving better result...
Honors & awards
Higher Secondary School Certificate Scholarship
Issued by Board of Intermediate and Secondary Examination, Jessore. | Jul 2016
Associated with Khulna Public Colleges
General Grade
Science Olympiad
Issued by Bangladesh Science Academy | Feb 2015
Associated with Khulna Public Colleges
Khulna Divisional Olympiad(place-15 combined)
Licenses & certifications
Mathematics For Machine Learning Specialization
Imperial College London
Issued Jun 2022 · No Expiration
Credential ID TZ5LRRW6MAK3
Python for Everybody Specialization
University of Michigan | Coursera
Issued Jun 2021 · No Expiration Date
Credential ID HWZ6W3K458VJ
Advanced Computer Vision with TensorFlow
Coursera
Issued Apr 2021 · No Expiration Date
Credential ID JU4BRSCVN5HT
Data Analyst with Python Track
DataCamp
Issued Apr 2021 · No Expiration Date
Credential ID dbdf71bf4c21d2b16aebe1e1363fd15d24c6ea05
Custom Models, Layers, and Loss Functions with TensorFlow
Coursera
Issued Mar 2021 · No Expiration Date
Credential ID 2CBGTQFP4K43
Convolutional Neural Networks in TensorFlow
Coursera
Issued Jan 2020 · No Expiration Date
Credential ID LZY7RHQCG7F3