Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Deep Learning - Convolutional Neural Networks
Rating: 3.8 out of 5(3 ratings)
541 students

Deep Learning - Convolutional Neural Networks

Easier way to learn Convolutional Neural Networks with Python
Created byYasir Amir
Last updated 6/2024
English
English [Auto],

What you'll learn

  • Convolutional Neural Networks (Deep Learning)

Course content

2 sections • 10 lectures • 3h 40m total length

  • Introduction31:20

    In this video we learn about the Convolutional Neural Networks very basics such as its layers and internal structure.

  • Convolution Layer of ConvNet8:51

    Understand the convolutional neural network's convolution layer by applying a 3-channel 3x3 filter to a 6 by 6 by 3 image, producing 4x4 feature maps with bias and ReLU.

  • Classical Neural Network LeNet12:37

    Explore LeNet-5, the pioneer of modern convolutional neural networks, built on gradient-based learning for document recognition, with a 32×32 grayscale input processed by conv and pooling layers.

  • Classical Network - AlexNet11:15

    Explore AlexNet, the 2012 ImageNet deep convolutional network that sparked modern CNN research. Trace its layered architecture from 11x11 filters with stride 4 and max pooling to 4096, 1000-class softmax.

  • Neural Networks in Controls14:03

    Explore direct inverse control with a multiple layer perceptron as the plant inverse. Train via backpropagation using reference input, tapped delay lines, and quadrotor Simulink demonstrations.

  • Convolutional Neural Networks - Quick Overview -22:07

    Explore how convolutional neural networks extract image features through convolution, ReLU, pooling, and a softmax classifier, with feature maps governed by depth, stride, and padding.

  • Convolutional Neural Networks - First Coding Example - (Matlab)10:00

    this lesson introduces convolutional neural networks with a first Matlab coding example using a pretrained AlexNet to classify images, showcasing CNN's ability to learn features directly from visual data.

  • Convolutional Neural Networks (CNNs) 1-Hour MCQ Assignment

Requirements

  • Machine Learning, Python

Description

Unlock the power of sight for machines! The age of intelligent vision is upon us, driven by the revolutionary capabilities of Convolutional Neural Networks (ConvNets). Want to be at the forefront of this exciting field? Learning ConvNets with Python is now easier than ever.

ConvNets have rapidly transformed computer vision, powering innovations from self-driving cars and automated medical image analysis to near-human facial recognition. This course provides a practical, accessible pathway to mastering these powerful tools. Gain the in-demand skills to build cutting-edge applications and shape the future of machine vision. Join the revolution and create the next generation of intelligent machines.

By the end, you'll be able to:

  • Explain ConvNets, their components (convolutional layers, pooling layers, activation functions), and their inner workings.

  • Design and code ConvNets using popular deep learning library like TensorFlow.

  • Critically analyze existing ConvNet designs and algorithms, identifying strengths and weaknesses for different tasks.

Ready for liftoff? This course ignites your AI and Machine Learning journey, providing the essential fuel and foundational skills you need to navigate this exciting and rapidly expanding universe. Think of it as your launchpad to the stars! While you'll gain the core competencies to explore this incredible frontier, the real adventure begins here. Dive deeper, push further, and never stop learning. This course is just the first step on your incredible AI exploration!

Who this course is for:

  • Artificial Intelligence Enthusiasts and (even Practitioners), Software Engineering students and professionals, Electrical Engineers,

Report abuse