Convolutional Neural Networks Lecture

You are in taxonomy page

Convolutional Neural Networks Lecture

Convolutional Neural Networks form the backbone of current AI revolution and are used in a multitude of classification and regression problems. This lecture overviews the transition from multilayer perceptrons to deep architectures. The following topics are resented in detail: Tensors and mathematical formulations. Convolutional layers. Fully connected layers. Pooling. Neural Image Features and their relation to human vision are discussed. Various types of convolutions are presented: Atrous (Dilated) Convolution, 1×1 convolution, separable convolutions.  Training convolutional NNs is detailed, including. Initialization, Data augmentation, Batch Normalization, Dropout, Regularization. Various CNN architectures are presented: Siamese Networks, FRACTALNET, DenseNet, Inception, ResNets, Squeeze and Excitation, Network-In-Network, AlexNet / ZFNet,  Deployment on embedded systems. Lightweight deep learning.

Should you require access to the resource, please contact the author directly.

Multilayer perceptron. Backpropagation

This lecture covers the basic concepts and architectures of Multi-Layer Perceptron (MLP), Activation functions, and Universal Approximation Theorem. Training MLP neural networks is presented in detail: Loss types, Gradient descent, Error Backpropagation. Training problems are overviewed, together with solutions, e.g., Stochastic Gradient Descent, Adaptive Learning Rate Algorithms, Regularization, Evaluation, Generalization methods.

Should you require access to the resource, please contact the author directly.

1D Convolutional Neural Networks

This lecture overviews 1D Convolutional Neural Networks that has many applications in 1D signal analysis. It covers the following topics in detail: 1D Convolution, 1D CNN Architecture, Convolutional Layer, Fully Connected Layer, Pooling Layers, Activation Functions, Supervised Learning, Classification/Regression, 1D CNN Training, 1D CNN applications (ECG monitoring, Music tagging).

Should you require access to the resource, please contact the author directly.

Bayesian Learning

This lecture overviews Bayesian Learning that has many applications in pattern recognition and clustering. It covers the following topics in detail: Bayes probability theorem. Bayes decision rule. Bayesian classification. Maximum A-Posteriori Criterion. Maximum Likelihood Criterion. Normally Distributed Sample Classification. Bayesian clustering.

Should you require access to the resource, please contact the author directly.

AI Science and Engineering and its Impact on the Society

This CVML Web Module focuses on the “Introduction to AI Science and Engineering and its impact on the society and Environment”. It is ideal for personnel upskilling and reskilling on AI. The Module content can be configured on demand. It consists of 16 lectures covering some of the following topics:

  • Introduction to AI Science and Information Technology,
  • AI Science, Mind and Humans,
  • AI Science and Society,
  • AI Science and the Environment.

Should you require access to the resource, please contact the author directly.

AI Studies

AI is a rapidly emerging field that has opened up new vistas of innovation and creativity. From intelligent systems to self-driving cars, AI has transformed the way we live and work. While AI is often studied as a subfield of computer science, it has grown so rapidly that it now encompasses many other fields. The World Economic Forum predicts a 37% increase in AI-related jobs by 2025. Therefore, it’s possible to imagine AI as a standalone field of study, independent of computer science.

This lecture lists all the available AI educational programs provided by countries across the globe.

Should you require access to the resource, please contact the author directly.