Convolutional Neural Network

Name: Convolutional Neural Network
Rating: 5.0 (2 reviews)

Learn the fundamental aspects to design a convolutional neural network architectures by given steps of modeling

Created byElhou kobz

Last updated 3/2021

English

What you'll learn

The overview of the deep learning field
Steps to design a Convolutional Neural Network models
Limitation, future, and challenges of Convolutional Neural Networks
The Convolutional Neural Networks models
The Hardware involved for CNN
Software used for CNN
The application of CNN

Course content

4 sections • 18 lectures • 56m total length

The general Introduction2:57
Explore the general introduction to convolutional neural networks, covering artificial intelligence foundations, deep learning, network architecture, training optimization, hardware and software, and practical applications.

What means the deep learning ?1:15
Why computational Intelligence algorithms are used ?0:54
Discover why computational intelligence algorithms solve problems beyond classical algorithms. Learn how they address human factors and enable adaptive systems that design human assistance and seek optima in complex problems.
Biomimetics inspiration of CNN from brain1:26
Classification of deep learning (CNN)1:32
Explore how convolutional neural networks classify images using supervised learning, including diagnostics, weather and market forecasting, customer segmentation, dimensionality reduction, and reinforcement learning for navigation.
The kinds of deep learning algorithms1:37
The definition of convolutional neural networks1:10
Define convolutional neural networks and explain their architecture for extracting features from images and videos, with hidden layers and a fully connected network after flattening.
Advantages of Convolutional Neural Network1:30
Explore the advantages of convolutional neural networks: automatic feature detection, local connections that reduce dimensionality, and superior performance versus traditional neural networks, with efficient initialization.

The purpose of CNN6:00
Explain the aim of convolutional neural networks and how they convert images into learned features for classification, using a fully connected classifier after CNN feature extraction.
Architecture of CNN21:11
Explore the architecture of a convolutional neural network, from RGB input and convolutional feature maps to non-linear activation, pooling, and fully connected layers with softmax classification.
Training and optimization of CNN parameters3:31
Hardware material used for CNN1:20
Explore hardware options used to accelerate cnn reasoning and facilitate implementation, including microprocessors, microcontrollers, graphics processing units, field programmable gateway, and neuro processing units.
Software used for deep learning1:21
Explore software used for deep learning and convolutional neural networks, including libraries and Microsoft Cognitive Toolkit, to design convolutional neural network architectures.
The famous CNN architectures1:46
The application of CNN2:17
Explore the applications of convolutional neural networks across object classification, semantic segmentation, text classification, image captioning, face recognition, gender prediction, depth estimation, and big data prediction.

Requirements

The basis of math (Convolution multiply, matrix, probability, vectors)
The basic knowledges of the image and video processing
Tensors, Matrices, and vectors
The logique operators and gates

Description

Artificial intelligence is a large field that includes many techniques to make machines think, which means endowing this machine with intelligence, unlike, as we all know, the habitual intelligence exhibited by humans and animals. Therefore, in this course, we investigate the mimicking of human intelligence on machines by introducing a modern algorithm of artificial intelligence named the convolutional neural network, which is a technique of deep learning for computers to make the machine learn and become an expert. In this course, we present an overview of deep learning in which, we introduce the notion and classification of convolutional neural networks. We also give the definition and the advantages of CNNs. In this course, we provide the tricks to elaborate your own architecture of CNN and the hardware and software to design a CNN model. In the end, we present the limitations and future challenges of CNN.

The essential points tackled in this course are illustrated as follows:

- What is deep learning?

- Why are computational intelligence algorithms used?

- Biomimetics inspiration of CNN from the brain

- Classification of deep learning (CNN)

- The kinds of deep learning algorithms

- Definition of convolutional neural networks

- Advantages of Convolutional Neural Network

- The pupose of CNN

- Architecture of CNN

- Training and optimization of CNN parameters

- Hardware material used for CNN

- Software used for deep learning

- Famous CNN architecture

- Application of CNN

- Limitation of CNN

- Future and challenges of convolutional neural networks

- Conclusions

Who this course is for:

Engineering Academics
The passion and Interest for learning concepts of artificial intelligence
University students of Computer Science
Students of Computer Vision
The students of Automatic

Convolutional Neural Network

What you'll learn

Explore related topics

Course content

General introduction1 lecture • 3min

The deep learning7 lectures • 9min