Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content
/ CENG Public

All the homeworks, testers and projects done at METU-CENG

License

Notifications You must be signed in to change notification settings

kadircet/CENG

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

METU CENG 2013-Present

Some intro to ceng/cs stuff written in python

Every assignment given in the course

Some verilog stuff

Many tasks done in prolog, haskell, and c++ to understand concepts in different programming languages.

Bomb Lab

A task which aims to make people familiar with reverse engineering

Attack Lab

A task which aims to teach people how to smash the stack for fun & profit

Performance Lab

A task which aims to teach optimization methodoligies for x86(64) architecture

HW1

Simple shell for linux.

HW2

Threading mutexes and semaphores practice for linux.

HW3

EXT2 filesystem defragmentation which moves every data block to begining of the disk.

Codes developed to perform various tasks on a PIC18F8722 based board. Both in assembly and C, even a simple RTOS project.

SRS

SDD

Homeworks and project done during 2016-2017 Spring Semester. No learning framework has been used in neither homeworks nor the project all codes have been written in python from scratch using only numpy, without help of any frameworks.

k-Nearest Neighbor
SVM/Softmax Classifier
Fully Connected Networks for regression/classification
Image classification
Next Character Prediction using Fully Connected Networks

Denoising Auto Encoders
CNNs
Saliency Maps
Fooling CNNs
Deep Dreaming
CIFAR-10 Dataset
TinyImageNet-100-A

Vanilla RNNs
LSTMs
Image Captioning using Microsoft COCO Dataset
Next Character Prediction using RNNs and LSTMs

Basic Question Answering using synthetic dataset generated in Turkish.
Dataset Generator
3 Different approaches using RNNs and Fully connected layers
Comparison of those approaches