alif2499 Goto Github PK

alif2499.github.io

Hello! this is Md. Alif Rahman Ridoy. I have created this repository for hosting my portfolio website from where you can know all about my background & achievements.

bccd_dataset

BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.

binary-classification-of-white-blood-cells-using-convoulutional-neural-network

This notebook contains the binary classification of White Blood Cells also known as Leukocytes using Convolutional Neural Network.

binary-classification-using-cnn-for-beginners

Here a Convolutional Neural Network is implemented to perform the classification between car or truck.

building-your-deep-neural-network-step-by-step

coursera-test

Coursera test repository

covid-19-detection-using-transfer-learning

In this notebook, the COVID-19 detection is performed using the COVID-19 Chest X-ray Image Dataset. The dataset contains chest X-ray images of normal and COVID-19 affected patients. Here, a convolutional neural network is adopted to extract features and classify images as normal and COVID-19 affected.

data-preprocessing-for-beginners

Here the data preprocessing is shown step by step.

deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

deep-neural-network-application-v8

digit-recognizer-using-ensemble-method-in-cnn

In this version of my notebook, I have used the ensemble method using Sequential Convolutional Neural Network for digits recognition trained on MNIST dataset. I choosed to build it with keras API (Tensorflow backend) which is very intuitive. Firstly, I will prepare the data (handwritten digits images) then i will focus on the CNN modeling and evaluation.

face-detection-in-an-image

Here it shows how to detect dace in any image. The coding is performed in python. It is a very basic and simple coding performed in OpenCV calling various image processing libraries.

gradient-checking-v1

Welcome to the final assignment for this week! In this assignment you will learn to implement and use gradient checking. You are part of a team working to make mobile payments available globally, and are asked to build a deep learning model to detect fraud--whenever someone makes a payment, you want to see if the payment might be fraudulent, such as if the user's account has been taken over by a hacker. But backpropagation is quite challenging to implement, and sometimes has bugs. Because this is a mission-critical application, your company's CEO wants to be really certain that your implementation of backpropagation is correct. Your CEO says, "Give me a proof that your backpropagation is actually working!" To give this reassurance, you are going to use "gradient checking".

hackerrank-solutions

Here are some solution to the hackerrank coding problems

image-classification-with-cnn-using-keras

Here in this project the cifar10 dataset has been used to classify the images. Among all the classes only three classes were chosen for this process. The link to the dataset is also provided here in the README file.

initialization

Welcome to the first assignment of "Improving Deep Neural Networks".

live_face_detection

Here the live face detection using webcam is demonstrated. The coding language used here is Python. Here some function are called to perform the detection.

logistic-regression-with-a-neural-network-mindset

This is the first assignment of the deep learning.ai specialization course on Coursera.

multi-class-classification-of-white-blood-cells-using-cnn

This notebook contains the multi-class classification of White Blood Cells using Convolutional Neural Network.

multiple-linear-regression

Contains the code to perform multiple linear regression.

neural-network-lab-assignments

This repository contains the assignments from CSE 4204 (Sessional of Neural Networks and Fuzzy Systems).

optimization-methods

Until now, you've always used Gradient Descent to update the parameters and minimize the cost. In this notebook, you will learn more advanced optimization methods that can speed up learning and perhaps even get you to a better final value for the cost function. Having a good optimization algorithm can be the difference between waiting days vs. just a few hours to get a good result.

planar-data-classification-with-one-hidden-layer

Planar data classification with one hidden layer coursera assignment.Part of deep Learning.ai specialization course

pneumonia-detection-using-convolutional-neural-network

In this notebook, I tried to differentiate the Normal and Pneumonia affected patients using chest X-ray images using a Lightweight Convolutional Neural Network. As a beginner myself, I searched a lot to perform prediction with higher acccuracy but less number of parameters thus know the difficulties and misunderstanding in the way. That's why, Here I will try my best to explain every steps for the sake of better understanding. Hope this will help the beginners like me to learn the basic image classification using CNN.

regularization_v2a

Welcome to the second assignment of this week. Deep Learning models have so much flexibility and capacity that overfitting can be a serious problem, if the training dataset is not big enough. Sure it does well on the training set, but the learned network doesn't generalize to new examples that it has never seen! You will learn to: Use regularization in your deep learning models.

simple-linear-regression

Contains the code to perform simple linear regression

some-basic-c-code-for-practice

This repository contains some of the C codes I had done during my undergrad studies. They are very basic and solutions for small problems. Anyone with very limited understanding of C , can get these. Hope these will help.

some-codes-for-practice

tensorflow-tutorial

Welcome to this week's programming assignment. Until now, you've always used numpy to build neural networks. Now we will step you through a deep learning framework that will allow you to build neural networks more easily. Machine learning frameworks like TensorFlow, PaddlePaddle, Torch, Caffe, Keras, and many others can speed up your machine learning development significantly. All of these frameworks also have a lot of documentation, which you should feel free to read

tumor-image-classification

In this notebook the CNN is used to classify brain tumor images.