Sina Soltani's Projects
32-bit pipelined MIPS CPU using Verilog with booth multiplication algorithm (faster multiplication in hardware). Xilinx Sesign Suite
I implemented logistic regression model from scratch with python and numpy. I used it to train a model for predicting diabetes. The dataset of diabetes is a csv file. I created a GUI as well(with tkinter) as well.
Character level language model create dinosaur names Coursera sequence models
Look, C-Scan, Scan , C-Look disk scheduling algorithms for OS implemented using python
deep neural networks implementation from scratch in coursera.com
find a short walk that traverses all nodes in a graph
Tensorflow and convolutional neural networks
Improvise a Jazz Solo with an LSTM Network
I used two Atmega32 AVR microcontrollers with SPI protocol and Master/Slave connection. Other elements: LM35 temperature sensor and a LCD and cooler Motors and heater and blinking warning LED. Using analog to digital converter and analog comparator. Using C programming to program the microcontrollers and Proteus. Compares the temperatures and shows it on a 16*2 alphanumeric LCD and depending on the temperatures either the cooler or the heater or the Red warning light.
modify word embeddings to reduce their gender bias
Neural Machine Translation (NMT) model to translate human-readable dates ("25th of June, 2009") into machine-readable dates ("2009-06-25"). using an attention model. sequence model Coursera assignment
Refined D-ary minheap in which the children of each node are stored in a built in binary heap so that finding the minimum a node's children is faster. The binary min heap uses the array of D-ary minheap and its within it and does not use separate array. .Implemented for Dijkstra's algorithm for shortest paths in a weighted directed graph.
Building your Recurrent Neural Network - Step by Step coursera
Config files for my GitHub profile.
implement the components of the transformers model in TensorFlow 2.4. sequence model coursera assignment
implement an algorithm for trigger word detection (sometimes also called keyword detection, or wake word detection). it detects you saying "activate."