The Difference Between AI, Machine Learning, and Deep Learning? | NVIDIA Blog

Artificial Intelligence — Human Intelligence Exhibited by Machines

Back in that summer of ’56 conference the dream of those AI pioneers was to construct complex machines — enabled by emerging computers — that possessed the same characteristics of human intelligence. This is the concept we think of as “General AI”

What we can do falls into the concept of “Narrow AI.” Examples of narrow AI are things such as image classification on a service like Pinterest and face recognition on Facebook.

Machine Learning — An Approach to Achieve Artificial Intelligence

As it turned out, one of the very best application areas for machine learning for many years was computer vision, though it still required a great deal of hand-coding to get the job done. People would go in and write hand-coded classifiers like edge detection filters so the program could identify where an object started and stopped; shape detection to determine if it had eight sides; a classifier to recognize the letters “S-T-O-P.” From all those hand-coded classifiers they would develop algorithms to make sense of the image and “learn” to determine whether it was a stop sign.

Deep Learning — A Technique for Implementing Machine Learning

Neural Networks are inspired by our understanding of the biology of our brains – all those interconnections between the neurons. But, unlike a biological brain where any neuron can connect to any other neuron within a certain physical distance, these artificial neural networks have discrete layers, connections, and directions of data propagation.

Each neuron assigns a weighting to its input — how correct or incorrect it is relative to the task being performed. The final output is then determined by the total of those weightings.

Tombone’s Computer Vision Blog: Deep Learning vs Machine Learning vs Pattern Recognition

Machine Learning: Smart programs can learn from examples

As Machine Learning grew into a major research topic in the mid 2000s, computer scientists began applying these ideas to a wide array of problems. Researchers started applying Machine Learning to Robotics (reinforcement learning, manipulation, motion planning, grasping), to genome data, as well as to predict financial markets. Machine Learning was married with Graph Theory under the brand “Graphical Models,” every robotics expert had no choice but to become a Machine Learning Expert, and Machine Learning quickly became one of the most desired and versatile computing skills.

Deep Learning: one architecture to rule them all

The most popular kinds of Deep Learning models, as they are using in large scale image recognition tasks, are known as Convolutional Neural Nets, or simply ConvNets.

QUESTION: 什么是卷积?

If you’re starting out with Deep Learning, simply brush up on some elementary Linear Algebra and start coding. I highly recommend Andrej Karpathy’s Hacker’s guide to Neural Networks. Implementing your own CPU-based backpropagation algorithm on a non-convolution based problem is a good place to start.

QUESTION: 什么是 CPU-based algorithm on a non-convolution based problem