aaaastark
Author | Research Scientist | Senior AI & ML Engineer | Generative AI Engineer
NVIDIA | Qorden AI | Datafy AssociatesLahore, Pakistan
Pinned Repositories
aaaastark
aaaastark
adversarial-network-attack-noise-on-mnist-dataset-pytorch
Adversarial Network Attacks (PGD, pixel, FGSM) Noise on MNIST Images Dataset using Python (Pytorch)
Deep-Learning
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep-learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, machine vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance. Artificial neural networks (ANNs) were inspired by information processing and distributed communication nodes in biological systems. ANNs have various differences from biological brains. Specifically, neural networks tend to be static and symbolic, while the biological brain of most living organisms is dynamic (plastic) and analog. The adjective "deep" in deep learning comes from the use of multiple layers in the network. Early work showed that a linear perceptron cannot be a universal classifier, and then that a network with a nonpolynomial activation function with one hidden layer of unbounded width can on the other hand so be. Deep learning is a modern variation which is concerned with an unbounded number of layers of bounded size, which permits practical application and optimized implementation, while retaining theoretical universality under mild conditions. In deep learning the layers are also permitted to be heterogeneous and to deviate widely from biologically informed connectionist models, for the sake of efficiency, trainability and understandability, whence the "structured" part.
False-Data-Injection-Attack
False Data Injection Attack (FDIA) with Long Sort Term Memory (LSTM) Model using Python
Goal-Kicker-Notes-Professional-Programming-Languages
Goal-Kicker-Notes-Professional-Programming-Languages (goal kicker)
Human_Resource_Management_System
Website to Human Resource Management System of the Employee Dashboard.
hybrid-model-with-cnn-lstm-python
Hybrid Model with CNN and LSTM for VMD dataset using Python
Intrusion-Detection-System
Attack Detection, Parameter Optimization and Performance Analysis in Enterprise Networks (ML Networks) for Intrusion Detection System IDS.
Pretrain_Finetune_Transformers_Pytorch
Pre-Training and Fine-Tuning transformer models using PyTorch and the Hugging Face Transformers library. Whether you're delving into pre-training with custom datasets or fine-tuning for specific classification tasks, these notebooks offer explanations and code for implementation.
Top-Big-Data-Scientist-Questions-For-Interview
Top Big Tech Data Science Questions
aaaastark's Repositories
aaaastark/Goal-Kicker-Notes-Professional-Programming-Languages
Goal-Kicker-Notes-Professional-Programming-Languages (goal kicker)
aaaastark/Top-Big-Data-Scientist-Questions-For-Interview
Top Big Tech Data Science Questions
aaaastark/False-Data-Injection-Attack
False Data Injection Attack (FDIA) with Long Sort Term Memory (LSTM) Model using Python
aaaastark/Intrusion-Detection-System
Attack Detection, Parameter Optimization and Performance Analysis in Enterprise Networks (ML Networks) for Intrusion Detection System IDS.
aaaastark/Pretrain_Finetune_Transformers_Pytorch
Pre-Training and Fine-Tuning transformer models using PyTorch and the Hugging Face Transformers library. Whether you're delving into pre-training with custom datasets or fine-tuning for specific classification tasks, these notebooks offer explanations and code for implementation.
aaaastark/hybrid-model-with-cnn-lstm-python
Hybrid Model with CNN and LSTM for VMD dataset using Python
aaaastark/adversarial-network-attack-noise-on-mnist-dataset-pytorch
Adversarial Network Attacks (PGD, pixel, FGSM) Noise on MNIST Images Dataset using Python (Pytorch)
aaaastark/Human_Resource_Management_System
Website to Human Resource Management System of the Employee Dashboard.
aaaastark/NVIDIA-Speech-Artificial-Intelligence
NVIDIA Speech Artificial Intelligence. Speech AI Summit 2022.
aaaastark/aaaastark
aaaastark
aaaastark/Accelerometer-Sensors-Analysis
Time Series Analysis: Accelerometer Sensors of Object Inclination and Vibration. Time Series Analysis by using different (State of Art Models) Machine and Deep Learning. Recurent Neural Network with CuDNNLSTM Model, Convolutional Autoencoder, Residual Network (ResNet) and MobileNet Model.
aaaastark/Acoustic-Communication-Mimicking-Sea
Acoustic Communication Underwater Mimicking Sea Classification by Multiscale Deep Features Aggregation and Low Complexity, and Data Augmentation.
aaaastark/Hyperspectral_Image_Denoising_AAFEHDN
Hyperspectral Image Denoising using Attention and Adjacent Features Extraction Hybrid Dense Network
aaaastark/NeMo-WeightsBiases-TTS
Training and Tunning a Text to speech model with Nvidia NeMo and Weights and Biases
aaaastark/aaaastark.github.io
aaaastark/ElectronJS-Desktop-Application
Website convert into Desktop Application through the Electron JS
aaaastark/Framingham_Hart_Study_Cohort
Framingham_Hart_Study_Cohort
aaaastark/gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
aaaastark/graph-convolution-network-with-dimensional-redaction-and-differential-algorithms-python
Graph Convolution Network GCN with Dimensional Redaction and Differential Algorithms using Python
aaaastark/Hadoop-Insallation-Commands-WordCount
Hadoop: Installation, Commands and Word Count Example
aaaastark/Intrusion-Detection-System-MQTT-Enabled-IoT
Intrusion Detection System for MQTT Enabled IoT.
aaaastark/linkedin-scraping-python
LinkedIn Scraping using Python Programming Language
aaaastark/market-basket-apriori-arules-analysis-r
R Market Basket (Apriori and Arules) Analysis and Visualization
aaaastark/MPI-OpenMP
MPI and OpenMP program run in CPP programming language. Operating System: Linux
aaaastark/NBART-Multilingual-Translator
This repository contains a Python script that uses a pre-trained NBART (Neural Bidirectional AutoRegressive Transformer) model to perform multi-lingual translation tasks between several languages. The model was trained on multiple language pairs using data parallelism, allowing it to learn representations across all languages simultaneously.
aaaastark/NVIDIA-CUDA-Google-Colab
Deployment of NVIDIA-CUDA on Google Colab. With in examples codes (Vector Addition and Matrix Multiplication).
aaaastark/perceptron-neural-network
Artificial Natural Network Perceptron (Forward Pass and Back Propagation). Weights and Bias. Forward Pass: Net Input Function, Activation Function (Sigmoid). Threshold. Back Propagation: Binary Cross Entropy Loss, Computing Gradients/ Slopes/ Derivatives, Gradient Descent Step, Epoch.
aaaastark/TextClassification-NLP-Project
Dataset preparation, Feature Engineering, Model Building, Summary Statistics, Data Exploration by Visualizations, and Save File CSV
aaaastark/WordAssociation-MutualInformation-NLP-Project
Word Association and Mutual Information Project
aaaastark/zillow-real-estate-marketplace-company-scraping-python
Zillow Real Estate Marketplace Company the Scraping using Python