ADR Awareness Centre

This lecture overviews Fast 3D Convolution algorithms that has many applications in the fast implementation of 3D image and video filtering, 3D CNNs and motion estimation.

1D convolutions are extensively used in digital signal processing (filtering/denoising) and analysis (also through CNNs).  As their computational complexity is of the order O(N^2), their fast execution is a must.

This lecture overviews Graph Neural Networks that has many applications in Deep Learning, Signal and Video Analysis, Network Theory, Web Science and Social Media Analytics. It covers the following topics in detail: Introduction to Graphs.

This lecture overviews Adversarial Machine Learning that has many applications in DNN robustness and in privacy protection.

In this lecture, the limitations of Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) in effectively processing sequences are emphasized.

This lecture covers the basic concepts and architectures of Multi-Layer Perceptron (MLP), Activation functions, and Universal Approximation Theorem.