Sumeyye Agac's Projects
PyTorch implementation for Channel Distillation
Implementation of color quantization using k-means and connected components analysis algorithms from scratch
Different experiments to understand the impact of attention for Human Activity Recognition (HAR) purpose
Deep learning framework for wearable activity recognition based on convolutional and LSTM recurretn layers
Deepsense: a unified deep learning framework for time-series mobile sensing data processing.
Expectation-Maximization (EM) algorithm for Gaussian mixture model (GMM) from scratch
Implemention of a python program which can stitch input images together to create a single panoramic image, called blended image
Performed various Deep Learning techniques to detect Human Activity using Sequential Data detect human activities generated by sensor-based wearable devices
A simple movie classifier (good-bad) implementation using IMDB movie data
Implementation of logistic regression from scratch using stochastic gradient descent (SGD) algorithm
Implementation of a simple neural language model (multi-layer perceptron) from scratch for next word prediction
Implementation of a 3-layer CNN for object classification using tensorflow library
Analysis of a biometric system's verification performance using similarity matrices
Implementation of VAE where the encoder is an LSTM and the decoder is a CNN