Hasan Arif's repositories
AngryBirds
This is a PLAYABLE simple angry-bird-like game written on C using i-graphics tool \m/
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Cross-Site-Scripting-XSS-Attack
Cross-site scripting (XSS) is a type of vulnerability commonly found in web applications. This vulnerability makes it possible for attackers to inject malicious code (e.g. JavaScript programs) into victim’s web browser. Using this malicious code, attackers can steal a victim’s credentials, such as session cookies. The access control policies (i.e., the same origin policy) employed by browsers to protect those credentials can be bypassed by exploiting XSS vulnerabilities.
Hidden-Markov-Models-Viterbi-and-the-Baum-Welch-algorithm.
The aim is to model with a Hidden Markov Model (HMM), and implement the Viterbi and the Baum-Welch algorithm
implementation-of-convolutional-neural-network-for-an-image-classification-task-from-Scratch
1. Convolution layer: there will be four (hyper)parameters: the number of output channels, filter dimension, stride, padding. 2. Activation layer: implement an element-wise ReLU. 3. Max-pooling layer: there will be two parameters: filter dimension, stride. 4. Fully-connected layer: a dense layer. There will be one parameter: output dimension. 5. Flattening layer: it will convert a (series of) convolutional filter maps to a column vector. 6. Softmax layer: it will convert final layer projections to normalized probabilities.
Implementation-of-Perceptron-and-its-variants
Implement 2-class classifiers using – Basic perceptron algorithm – Reward and punishment (RP) algorithm – Pocket algorithm
LLFI-upgrade
LLFI is an LLVM based fault injection tool, that injects faults into the LLVM IR of the application source code. The faults can be injected into specific program points, and the effect can be easily tracked back to the source code. Please refer to the paper below. NOTE: If you publish a paper using LLFI, please add it to PaperLLFI.bib
Logistic-Regression-and-AdaBoost-for-Classification
In ensemble learning, we combine decisions from multiple weak learners to solve a classification problem. Here, I will implement a Logistic Regression (LR) classifier and use it within AdaBoost algorithm.
LUDO-with-JavaFX
This a conventional LUDO game code written in java and javaFX.
My-leetcode-Solve
targeting to solve leetcode problems on regular basis and gather them here ;-)
Rasterization-based-computer-graphics-Pipeline
4 stages of the pipeline. 1. Stage 1: modeling transformation 2. Stage 2: view transformation 3. Stage 3: projection transformation 4. Stage 4: clipping & scan conversion using Z-buffer algorithm
ShapeWorks
ShapeWorks
Template-Matching-in-a-video-using-exhaustive--logarithmic-and-hierarchical-search-techniques-
It tracks a reference object in a video file. The output will be another video file output.mov showing the location of the reference object using bounding boxes in each frame.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.