SIFT is a scale-invariant feature transform algorithm used to detect and describe local features in images. It detects keypoints that are invariant to scale, rotation, and partially invariant to illumination and viewpoint changes. The algorithm involves 4 main steps: (1) scale-space extrema detection, (2) keypoint localization, (3) orientation assignment, and (4) keypoint descriptor generation. SIFT descriptors provide a feature vector for each keypoint that is highly distinctive and partially invariant to remaining variations.
The document discusses image stitching, which involves combining overlapping images into a single larger image. It describes detecting feature points in images, finding corresponding point pairs, using the pairs to align images with a homography matrix, and blending the combined images. It outlines an image stitching algorithm that detects keypoints, matches features, estimates homography with RANSAC to handle outliers, and blends images with pyramid blending to minimize seams and ghosting.
This document summarizes notes from a deep learning report and exercises. It discusses topics like input and hidden layers, activation functions, output layers, gradient descent, backpropagation, and solutions to problems like vanishing gradients. Key points covered include how neural networks transform input data through weighted layers, common activation functions for different layers, calculating error using loss functions, using gradient descent to minimize error by adjusting weights, and backpropagation to efficiently calculate gradients. Exercises reinforce understanding of these concepts through coding implementations and analyzing results.
SIFT is a scale-invariant feature transform algorithm used to detect and describe local features in images. It detects keypoints that are invariant to scale, rotation, and partially invariant to illumination and viewpoint changes. The algorithm involves 4 main steps: (1) scale-space extrema detection, (2) keypoint localization, (3) orientation assignment, and (4) keypoint descriptor generation. SIFT descriptors provide a feature vector for each keypoint that is highly distinctive and partially invariant to remaining variations.
The document discusses image stitching, which involves combining overlapping images into a single larger image. It describes detecting feature points in images, finding corresponding point pairs, using the pairs to align images with a homography matrix, and blending the combined images. It outlines an image stitching algorithm that detects keypoints, matches features, estimates homography with RANSAC to handle outliers, and blends images with pyramid blending to minimize seams and ghosting.
This document summarizes notes from a deep learning report and exercises. It discusses topics like input and hidden layers, activation functions, output layers, gradient descent, backpropagation, and solutions to problems like vanishing gradients. Key points covered include how neural networks transform input data through weighted layers, common activation functions for different layers, calculating error using loss functions, using gradient descent to minimize error by adjusting weights, and backpropagation to efficiently calculate gradients. Exercises reinforce understanding of these concepts through coding implementations and analyzing results.
This document provides an overview of reinforcement learning including:
1. It defines reinforcement learning as a type of machine learning that enables agents to learn through trial-and-error using feedback from their actions and experiences.
2. It discusses an example of AWS Deepracer, which is a tool for learning reinforcement learning by racing autonomous cars in a simulated environment.
3. It explains key concepts in reinforcement learning including Markov decision processes, states, actions, rewards, policies, and value functions which are used to attain optimal solutions.
This slide is a revised version of my slide entitled "Introduction to Quantum Computer" shared about 5 months ago. It starts from a basic explanation between Bit and Qubit. It then follows with a brief history behind Quantum Computing and Engineering, current trends, and update with concerns to make the quantum tech practically useful.
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
A stale version, please check https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning-166237519 for a new version.
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
This document discusses several different installation systems for software applications including Nullsoft Scriptable Install System, Visual Studio Installer, Windows Installer XML toolset, and InstallShield. It appears to provide an overview of common installation options for software developers.
This document provides an overview of reinforcement learning including:
1. It defines reinforcement learning as a type of machine learning that enables agents to learn through trial-and-error using feedback from their actions and experiences.
2. It discusses an example of AWS Deepracer, which is a tool for learning reinforcement learning by racing autonomous cars in a simulated environment.
3. It explains key concepts in reinforcement learning including Markov decision processes, states, actions, rewards, policies, and value functions which are used to attain optimal solutions.
This slide is a revised version of my slide entitled "Introduction to Quantum Computer" shared about 5 months ago. It starts from a basic explanation between Bit and Qubit. It then follows with a brief history behind Quantum Computing and Engineering, current trends, and update with concerns to make the quantum tech practically useful.
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
A stale version, please check https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning-166237519 for a new version.
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
This document discusses several different installation systems for software applications including Nullsoft Scriptable Install System, Visual Studio Installer, Windows Installer XML toolset, and InstallShield. It appears to provide an overview of common installation options for software developers.