AI vs Machine Learning vs Deep Learning

Artificial Intelligence - Human Intelligence exhibited by Machines.

Machine Learning - An Approach to Achieve Artificial Intelligence.

Deep Learning - A Technique for Implementing Machine Learning.

Artificial Intelligence is a generalized form of Machine and Deep Learning and check this incredible post for detailed information.

Succinctly, Deep Learning is-a Machine Learning is-a(n) Artificial Intelligence.

Deep Learning

Deep Learning extends (IS-A a type of) Machine Learning by adding cascade of layers to efficiently exercise data patterns before predicting the outcome to the closest possible, which lead to some scenarios better than humans.

Today's driver-less cars do use this mechanism underneath.

Qt

Qt (pronounced cute) is a free and open-source widget toolkit for creating graphical user interfaces as well as cross-platform applications that run on various software and hardware platforms such as Linux, Windows, macOS, Android or embedded systems with little or no change in the underlying code base.

~ Wiki

Machine Learning

Machine Learning extends (IS-A type of) Artificial Intelligence (AI) by incorporating algorithms - are often categorized as supervised and unsupervised - into computers with an ability to learn without being explicitly programmed when exposed to the new data. 

AI

OpenCV

Open Source Computer Vision is a library of functions, designed for computational efficiency with a strong focus on real-time computer vision applications. Having written in optimized C/C++, the library can take advantage of multi-core processing. Enabled with OpenCL, so it can take advantage of the hardware acceleration of the underlying heterogeneous compute platform.

It has C, C++, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.

Deployed uses span the range from stitching street view images together, detecting intrusions in surveillance video, monitoring mine equipment, helping robots navigate and pick up objects, detection of swimming pool drowning accidents, checking runways for debris and inspecting labels on products in factories on to rapid face detection.

~ Wiki

Intel IPP

Intel® Integrated Performance Primitives is a multi-core, multi-OS and multi-platform ready, computationally intensive and highly optimized software library that meets all your Imaging, Vision, Signal, Storage and Security needs.

~ Wiki

OpenCL

Open Computing Language is the open standard for cross-platform, parallel programming diverse processors found in personal computers, servers, mobile devices and embedded platforms. It greatly improves the speed and responsiveness of a wide spectrum of applications including gaming, scientific, medical software, professional creative tools and vision processing etc...

To put it in a nutshell, the open standard for parallel programming of heterogeneous systems.

~ Wiki

CUDA vs OpenGL

CUDA is a parallel computing platform API, which extended the usage of GPU (which was otherwise used only for graphics processing) for general purpose processing. But the scope is limited to CUDA-enabled GPUs manufactured by NVIDIA only and does not work on different GPUs by other manufacturers. CUDA platform is designed to work with C, C++ and Fortran programming languages hence easier to code straight to GPU. Compatible with most standard operating systems.

e.g. Identify hidden plaque in arteries, Analyze air traffic flow and Visualize molecules etc...

OpenGL is a graphics library, which provides set of API that makes use of GPU (hardware-accelerated) to render graphics faster - focus is specific to rendering on GPUs. Supported on essentially every GPU. Required advanced skills in graphics programming. It is language and platform independent.

e.g. CAD, Virtual reality, Flight simulation and Video games etc...

CUDA

Compute Unified Device Architecture is a parallel computing platform and API to use a CUDA-enabled GPU for general purpose processing (GPGPU), which leads to dramatic increase in computing performance by harnessing the power of the GPU. 

The CUDA platform gives direct access to the GPU's virtual instruction set and parallel computational elements to execute compute kernels. Supports OpenCL programming framework.

~ Wiki