An introduction to AILet’s code an intelligent system

JNJD 2016INPT

PlANPart I: Fundamentals of AI

Overview of AIStatistics, Uncertainty, and Bayes networksMachine LearningLogic and PlanningMarkov Decision Processes and Reinforcement LearningHidden Markov Models and FiltersAdversarial and Advanced PlanningPart II: Applications of AIImage Processing and Computer VisionRobotics and robot motion planningNatural Language Processing and Information Retrieval

Human Intelligence ?!

the ability to acquire and utilize(link) knowledge to solve (novel) problems

Can we build hardware as complex as the brain?

How complicated is our brain?

a neuron, or nerve cell, is the basic information processing unit

estimated to be on the order of 10 12 neurons in a human brain

many more synapses 10 14) connecting these neurons

cycle time: 10 -3 seconds (1 millisecond)

How complex can we make computers?

108 or more transistors per CPU

supercomputer: hundreds of CPUs, 1012 bits of RAM

cycle times: order of 10 - 9 seconds

Conclusion

YES: in the near future we can have computers with as many basic processing elements as our brain, but with far fewer interconnections (wires or synapses) than the brain much faster updates than the brain but building hardware is very different from making a computer behave like a brain!

Artificial intelligence is intelligence in machine

AI is Science

Deep learning

the ability to act like humans

History of AI1943: early beginnings. McCulloch & Pitts: Boolean circuit model of brain (they modeled a simple neural network using electrical circuits)

1950: Turing.Turing's "Computing Machinery and Intelligence“

1956: birth of AI. Dartmouth meeting: "Artificial Intelligence“ name adopted

numerous applications and huge possibilities in the field of AI, which continues to expand human capability beyond our imagination

Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997

During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people

Is it AI?Test to determine whether or not machines were intelligent

Turing test

Chinese Room

Summary of State of AI Systems in PracticeSpeech synthesis, recognition and understanding

very useful for limited vocabulary applications

unconstrained speech understanding is still too hard

Computer visionworks for constrained problems (hand-written zip-

codes)

understanding real-world, natural scenes is still too hard

Learningadaptive systems are used in many applications: have their limits

Planning and Reasoningonly works for constrained problems: e.g.,

chess

real-world is too complex for general systems

Overall:many components of intelligent systems

are “doable”

there are many interesting research problems remaining

FrameWorkTensorflow

Caffe..

TensorFlow

is an Open Source ( Apache 2.0) Software Library for Machine

Intelligence www.tensorflow.org

TensorFlow comes with an easy to use Python interface and a no-nonsense C++ interface to build and execute your computational graphs. Write stand-alone TensorFlow Python or C++ programs, or try things out in an interactive TensorFlow iPython notebook where you can keep notes, code, and visualizations logically grouped. This is just the start though -- we’re hoping to entice you to contribute SWIG interfaces to your favorite language -- be it Go, Java, Lua, JavaScript, or R.

Demo (TensorFlow)Image recognition

Why is visual recognition a hard problem?

FuturIs really unknown but at this evolution rate it will become more and more complex.