Displaying 273 resources

Symbolic, Statistical, and Causal Representations

In machine learning, we use data to automatically find dependencies in the world, with the goal of predicting future observations.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

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.
Category
Data for AI, Systems, methodologies, hardware, and tools
Source
AI-OnDemand

Data Clustering

This lecture overviews Data Clustering  that has many applications in e.g., facial image clustering, signal/image clustering, concept creation.  It covers the following topics in detail: Clustering Definitions.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

Drone Swarms

This lecture overviews Drone Swarms that has many applications in autonomous drones.
Category
Data for AI, Systems, methodologies, hardware, and tools
Source
AI-OnDemand

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.
Category
Systems, methodologies, hardware, and tools, Recommendations towards policy changes
Source
AI-OnDemand

High-Dynamic Range Imaging

This lecture overviews High-Dynamic Range Imaging that has many applications in digital photography.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

Transfer Learning

This lecture overviews Transfer Learning (TL) that has many applications in DNN training and adaptation, Image Understanding, Text Mining, Activity Recognition, Bioinformatics, Transportation.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

Gray Box Optimization

In Gray Box Optimization, the optimizer is given access to the set of M subfunctions. We prove Gray Box Optimization can efficiently compute hyperplane averages to solve non-deceptive problems in time.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey

Keyphrase prediction aims to generate phrases (keyphrases) that highly summarizes a given document. Recently, researchers have conducted in-depth studies on this task from various perspectives.
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand

ECG Signal Analysis

This lecture overviews ECG Signal Analysis as well as other cardiology imaging methods that has many applications in cardiological disorder diagnosis and treatment. It covers the following topics in detail: Background nnowledge of ECG Signals.
Category
Data for AI, Systems, methodologies, hardware, and tools
Source
AI-OnDemand

Fast 1D Convolution Algorithms

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 will overview
Category
Data for AI, Systems, methodologies, hardware, and tools
Source
AI-OnDemand

An Introduction to PAC-Bayesian Analysis

This resource corresponds to 9th video from the AI Excellence Lecture Series. PAC-Bayesian Analysis is a framework in machine learning and statistics that combines ideas from the Probably Approximately Correct (PAC) learning framework and Bayesian p
Category
Systems, methodologies, hardware, and tools
Source
AI-OnDemand