Machine Learning/Artificial Intelligence

May 27, 2024

Part 3 – Projected Gradient Descent (PGD)

Thoviti Siddharth Machine Learning/Artificial Intelligence Adversarial Machine Learning, Fast Gradient Sign Method, FGSM, Machine Learning Hacking, PGD, PGD Attack, Projected Gradient Descent, PyTorch, ResNet50 0

Welcome to Part 3 of our blog series on Adversarial Machine Learning! In this installment, we will delve into the intricacies of the Projected Gradient Descent (PGD) method—a powerful iterative technique for crafting adversarial examples. We will explore how PGD enhances the Fast Gradient Sign Method (FGSM) by iterating and refining the perturbations, leading to more robust and effective attacks. I will also provide a step-by-step code implementation of PGD using PyTorch and compare the attack success rates of FGSM and PGD.

June 19, 2023

Part 2 – Fast Gradient Sign Method (FGSM)

Thoviti Siddharth Machine Learning/Artificial Intelligence Adversarial Attack, Adversarial Machine Learning, Fast Gradient Sign Method, FGSM, Fine-Tuning, PyTorch, ResNet50 0

Welcome to Part 2 of our blog series on Adversarial Machine Learning! In this installment, we will explore the Fast Gradient Sign Method (FGSM), one of the most widely used and effective adversarial attack techniques. We will understand how the attack works, its significance, and implement the attack through PyTorch code.

June 14, 2023

Part 1 – Introduction to Adversarial Machine Learning

Thoviti Siddharth Machine Learning/Artificial Intelligence Adversarial Example, Adversarial Machine Learning, Distance Metrics 0

Welcome to the first part of our blog series on Adversarial Machine Learning! In this series, we will explore the fascinating field of adversarial machine learning, its background, techniques for attacks, and strategies for defense. Let’s begin with an introduction to adversarial machine learning and its relevance in today’s landscape.

June 13, 2023

Fine-Tuning ResNet50 pretrained on ImageNet for CIFAR-10

Thoviti Siddharth Machine Learning/Artificial Intelligence CIFAR-10, Fine-Tuning, PyTorch, ResNet, Transfer Learning 0

Introduction

In this blog post, we will discuss how to fine-tune a pre-trained deep learning model using PyTorch. Fine-tuning is a powerful technique that allows us to leverage the knowledge learned by a pre-trained model on a large dataset and apply it to a new task. This can save a significant amount of time and resources compared to training a model from scratch. The fine-tuned model achieved 92.34% accuracy on the test set.

February 1, 2022

Summary of AlexNet

Thoviti Siddharth Machine Learning/Artificial Intelligence Alexnet, Alexnet-Summary, CNN, Computer Vision, DCNN, Dropout, ImageNet, Local Response Normalization, Machine Learning, Overfitting, Overlapping Pooling, ReLU, Summary, TanH 1

Title: ImageNet Classification with Deep Convolutional Neural Networks (2012)

Authors: Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

Point of the Paper: “GPU memory enables training large networks on large image datasets.”

At a time when human performance was achieved on relatively small image datasets like MNIST and CIFAR-10, computer vision researchers were eager to achieve the same with large, high-resolution image datasets. Although datasets such as ImageNet provided large and real-world data, simple convolution neural networks (CNN) did not perform well on such high-resolution datasets. Innovative trials were limited by computational resources. AlexNet solved these problems by introducing deep CNN that achieved the state-of-the-art in the ImageNet LSVRC-2010 contest, and GPU parallelization.

December 10, 2020

Traffic Sign Detection with Faster R-CNN

Thoviti Siddharth Machine Learning/Artificial Intelligence Computer Vision, Faster R-CNN, Finetuning, Machine Learning, Machine Vision, Object Detection, PyTorch 3

Autonomous vehicles that are capable of navigating without human inputs are heavily dependent on computer vision tasks such as object detection. Many object detection algorithms such as YOLO, Faster R-CNN, SSD, have been proposed to detect and recognize the traffic signs.

In this blog, Faster R-CNN will be used for the detection of German traffic signs (GTSDB dataset) with reference to Torchvision’s object detection finetuning tutorial.