-
Normal Cyst Tumor And Stone
The dataset comprises CT images of the kidneys, covering four distinct categories:
tumors, cysts, normal, and stones. I've implemented basic Convolutional Neural Networks (CNNs),
ResNet, and VGG architectures for image classification on these images.
-
Amazon Reviews
A machine learning model was developed and trained on Amazon Reviews to analyze user sentiment.
The dataset was extensively preprocessed, involving techniques such as tokenization, stopwords removal,
lemmatization, stemming, tag and emoji removal, and normalization.
The sentiment analysis task on Amazon reviews was conducted using Logistic Regression.
The repository provides resources and code for a variety of sentiment classification models,
including Embedding Models, BERT, and Simple Neural Networks.
-
An Odd Music Generator
This project aims to explore Autoencoders Denoising, data augmentation methods,
audio file processing, string-to-string models (Seq2seq), and intelligent systems.
The project consists of four key components: Denoising, Note Recognition, Note Prediction, and Noise
Maker.
I used an LSTM-based n-gram language model to predict the next musical note in a sequence,
supporting the development of well-structured musical compositions.
-
Multi Class Weather
I worked with the Multi-class Weather Dataset consisting of Rain, Shine, Sunrise, and Cloudy categories.
The project focused on computer vision, image processing,
and deep neural networks using models like ResNet and Inception with k-fold cross-validation for
evaluation.
-
Analyzing Human Metaphase II Oocyte Images
This project serves as an example of semantic segmentation,
featuring the implementation of a robust deep learning-based multiclass semantic segmentation method.
It is specifically designed for analyzing human metaphase II oocyte images, as outlined in a
paper
-
NLP Subject Similarity
The project includes sentence pairs with sentence1 and sentence2,
scored for textual similarity, amenable to regression or classification using neural networks.
The project utilizes neural networks for similarity analysis, involving Data Labeling,
Multi-label RNN Classification, Text Preprocessing, and Classification Networks.
-
Students Academic Performance
The project aimed to utilize a custom neural network structure created from scratch
(Neural Networks from Scratch) for predicting student acceptance or rejection during an
academic semester based on their characteristics. Furthermore, TensorFlow was employed to
achieve the same objective.
-
Trie
For my university's Data Structure course project, I developed a student management system.
I utilized a HashTable to store student data indexed by their IDs and implemented a
Trie tree to store HashTable's keys.
-
Four In Row
The game is set in single-player mode, with an AI Agent using the Negamax algorithm.
This algorithm calculates the minimum value of child nodes in one step and subsequently
selects the maximum value among these minimum values as the value for the parent node in the next step.