Computer Vision

Overview

Dive into a comprehensive 3.5-hour course on computer vision, exploring machine learning fundamentals, neural networks, and advanced architectures. Learn about supervised and unsupervised learning, data processing techniques, and model evaluation. Discover key computer vision applications and image representation methods. Explore essential neural network components, including neurons, activation functions, and convolutions. Examine popular architectures like LeNet, AlexNet, VGG, and ResNet. Delve into object detection techniques, including bounding boxes, anchor boxes, and models such as R-CNN and YOLO. Investigate semantic segmentation and fully convolutional networks, culminating with the U-Net architecture. Gain hands-on experience using Jupyter Notebooks on SageMaker to reinforce your learning.

Syllabus

Accelerated Computer Vision 1.1 - Intro.
Accelerated Computer Vision 1.2 - Introduction to Machine Learning.
Accelerated Computer Vision 1.3 - ML Applications.
Accelerated Computer Vision 1.4 - Supervised and Unsupervised Learning.
Accelerated Computer Vision 1.5 - Data Processing - Imbalanced Data.
Accelerated Computer Vision 1.6 - Underfitting, Overfitting and Model Evaluation.
Accelerated Computer Vision 1.7 - Computer Vision Applications.
Accelerated Computer Vision 1.8 - Image Representation.
Accelerated Computer Vision 1.9 - Neuron & Activation Functions.
Accelerated Computer Vision 1.10 - Neural Networks: Components and Training.
Accelerated Computer Vision 1.11 - Convolutions (Filters).
Accelerated Computer Vision 1.12 - Padding, Stride and Pooling.
Using Jupyter Notebooks on Sagemaker.
Accelerated Computer Vision 2.1 - Computer Vision Datasets.
Accelerated Computer Vision 2.2 - LeNet.
Accelerated Computer Vision 2.3 - AlexNet.
Accelerated Computer Vision 2.4 - Transfer Learning.
Accelerated Computer Vision 3.1 - VGG and Batch Normalization.
Accelerated Computer Vision 3.2 - ResNet.
Accelerated Computer Vision 3.3 - Object Detection Applications.
Accelerated Computer Vision 3.4 - Bounding Box and Anchor Box.
Accelerated Computer Vision 3.5 - Sliding Window Method and Non-max Suppression.
Accelerated Computer Vision 3.6 - Region Based Convolutional Neural Networks (R-CNNs).
Accelerated Computer Vision 3.9 - Fully Convolutional Networks.
Accelerated Computer Vision 3.7 - You Only Look Once (YOLO) model.
Accelerated Computer Vision 3.8 - Semantic Segmentation.
Accelerated Computer Vision 3.10 - U-Net.
MLU Channel Introduction.