Introduction

to AI
What is Artificial Brain/Mind?
 “You, your joys, and your sorrows, your memories and your
ambitions, your sense of personal identity and free will, are in
fact no more than the behavior of a vast assembly of nerve cell
and
their associated molecules.”
Francis Crick

 Because we do not understand the brain very well we are

constantly tempted to use the latest technology as a model for
trying to understand it. In my childhood we were always assured
that the brain was a telephone switchboard (‘What else could it
be?’).
John R.
Searle

 How to theorize the artificial modeling of human feelings,

thoughts, and actions?

2
 The Physical Symbol System Hypothesis
 (PSSH)
Intelligence actions can be modeled by a system manipulating symbols.
Formal
 “A physical symbol system consists of a set of entities, called symbols,
Logic/Algebra
which are physical patterns that can occur as components of another type
of entity called an expression (or symbol structure).
Digital
 A physical symbol system has the necessary and sufficient means for Computer
performing intelligent actions. So, it is a modelling platform. At any
instant of time the system will contain a collection of these symbol
structures.
Chess
 A symbol structure is composed of a number of instances (or tokens)
of symbols related in some physical way (such as one token being next
to another).

 Besides these structures, the system also contains a collection of processes

that operate on expressions to produce other expressions: processes of
creation, modification, reproduction, and destruction.”

 How to implement the artificial modeling of human feelings, thoughts,

and actions?
3
 Can Machines Think?
 “The new problem has the advantage of drawing a fairly sharp line between the physical
and the intellectual capacities of a man.” (Turing, 1950)

 Machines with Thinking Abilities:

 A Turing machine is a mathematical model of a physical computing device.
 Any given problem for which a Turing machine can provide solution, it can
be provided by the physical machine as well.
 Formulation: Every function that can be naturally regarded as computable can
Alan Turing depicted on the
be computed by a Turing machine. Loebner Prize Gold Medal.
 Can we create intelligence using machines?

 The Arguments about Questioning the Thinking Ability of Machines? Given that the
nervous system is not a discrete-state machine, you cannot mimic the behavior of nervous
system with a discrete-state machine (Continuity in the Nervous System).

 Machines with thinking capabilities: Ctesibius of Alexandria - Water Clock with a

Regulator and Thermostat of Wiener - Controller of the Environment Temperature.

 How about having a machine capable of having human feelings and thoughts, and Automated device for playing chess
and performing arts .
performing actions?
4
 Turing Machine and Turing Test
 Turing Machine:
 A finite state machine with Governing each transition by the input
symbol, the current state, and the corresponding entry in the transition
table.
 The next state is stored into the state register and the output is written to the
cell.
 Transition Table: A set of entries in the format of
{<Current State, Input Symbol>  < Next State, Output Symbol, Move>}
 When we do prediction, we use a sort of intelligence!

 Turing Test:
 A machine can be described as thinking machine if it passes the Turing
Test. This test evaluates the intelligence.
 If a human agent is engaged in two isolated dialogues (connected
by teletype), one with a computer, and the other with another
human.
 The human agent cannot reliably identify which dialogue is with
the computer due to its kind of intelligence.
 A human communicates with a computer via a teletype. If the human
cannot tell he is talking to a computer or another human, it passes the test.
Text
?
Cognition
Text
 How does the machine with thinking ability perform and how to test it? 7
 AI: How to Define AI?
 The term got coined by John McCarthy in 1956 when a group of when scientists began exploring how computers
could solve problems on their own..

 Def. 1 by David Marr: “AI is the study of complex information processing problems that often have their roots in
some aspects of biological information processing. The goal of the subject is to identify solvable and interesting
information
processing problems, and solve them.”

 Def. 2 by Rodney Brooks: “The intelligent connection of perception to action.”

 Def. 3 by Alan Turing: “Actions that are indistinguishable from a human’s ones.”

 How to simply define AI? A machine with the ability to perform cognitive functions such as perceiving, learning,
reasoning and solve problems are deemed to hold an artificial intelligence. The benchmark for AI is the human
level concerning reasoning, speech, and vision.

 How to well define AI? We can define intelligence as the computational part of the ability to achieve goals in
the world. Varying kinds and degrees of intelligence occur in humans, many animals and some machines. It is
the capacity to learn and solve problems in particular tacking novel problems, act rationally, and act like
humans.

 How to define AI and what properties and characteristics to include in AI? 6

AI: Different Views on AI
 Philosophy, Ethics, and Religion:
 What is intelligence?
 Is there any formal expression?
 How to define mind as a machine with internal operations?

 Cognitive Science, Neuroscience, Psychology, and Linguistics:

 Understand natural forms of intelligence.
 Learn principles of intelligent behavior.

 Engineering:
 Can we build intelligent devices and systems?
 Autonomous and semi-autonomous for replicating human capabilities,
improving performance, and so forth.

7
 AI: What is Inside AI?
 Applications:  Software/Hardware:
 Image and Speech Recognition  Graphical Processing Unit
 Natural Language Processing  Parallel Processing Tools (e.g. Spark)
 Autonomous Driving  Cloud Data Storage and Computing System

 Types of Models:  Programming Languages and Libraries:

 Artificial Intelligence  Python, MATLAB, Java, and C++
 Machine Learning  TensorFlow, Keras, PyTorch, OpenCV, and Caffe
 Deep Learning
Artificial Intelligence

Convolutional
Tree Graph Bayesian
Neural
Search Search Networks
Network

State-Based Model Variable-Based Model

Parametric, Reflex Model Logic-Based Model

Artificial Support First-

Propositional
Neural Vector Order
Logic
Network Machine Logic

8
 AI: Brain Neural Network
 While brain is heterogenous, it is composed of neurons.

 A neuron transmits/receives signal to/from other neurons (generally

thousand) via its connected synapses. The signal is chemically based.

 A neuron can be in either an Excited or an Inhibited state at any point

in time.

 The signal strength is high in Excited state and is low in Inhibited state.

 Inputs are approximately summed.

 When the input exceeds a threshold the neuron sends an electrical

spike that travels throughout the body, gets to the axon, and reaches to
next neuron(s).

 How to create a computer neural network based on the brain neural

network?

 As we learn new things, new strong neural pathways (i.e. a series of

connected neurons) in our brain are formed.
9
 AI: Modelling of Brain Neural
Network

 “In our view, people are smarter than today’s computers because the brain employs a basic computational architecture
that is more suited to deal with a central aspect of the natural information processing tasks that people are so good
at.”
 Assumption: Mental phenomena can be described by interconnected networks of simple and often uniform units.
 Can we build a functional brain using computers?
1
0
History of AI
Beginning: 1943 –
1952
1943: J. McCulloch, W. Pitts: model of the artificial neuron
1949: D. Hebb: rule to modify the connection strength
between two neurons
1951: Minsky and Edmons: the first neural network
containing 40 neurons (vacuum tubes)
1950: A. Turing: Turing test, machine learning, genetic
algorithms, reinforcement learning

IAI –
1952 – 1969: Early enthusiasm, high hopes (1)

1952: A. Samuel: game of checkers, a

program that learns
1956: Newell, Shaw and Simon: Logic
Theorist (LT) – a shortened proof of a
theorem from the book Principia
Mathematica
1957: Newel & Simon: GPS, the first
program that embodied the human way of
thinking
1958: J. McCarthy: LISP
1960 – 1962: Widrow i Hoff: Adaline
1962: F. Rosenblatt: proof of
perceptron convergence

IAI –
1952 – 1969: Early enthusiasm, high hopes (2)

1965: Joseph Weizenbaum – ELIZA

chatterbot 1965: Robinson – resolution
rule
1966: Quillian – semantic networks
1969: Minsky & Papert: “Perceptrons” – a limitation
of neural networks

IAI –
 1952 – 1969: Sobering up (1)
Early systems performed poorly when applied to a wider
range of problems or on more difficult problems
Early systems contained little or no knowledge, the output
was the result of relatively simple syntactic manipulations

First failure of machine translation

(1957)
Machine translation (financed to
speed up translating Russian papers
on Sputnik) was based on syntactic
transformations and word substitution
using English and Russian gram- mars.
The result:
“The spirit is willing but the flesh is weak”
→ “The vodka is good but the flesh is rot-
ten”

IAI –
1952 – 1969: Sobering up (2)

Another big problem – intractability of many problems that

AI was trying to solve
Initial success was possible because the problems were
reduced to “microworlds” with only a handful of
combinations
Before the development of computability theories, it was
believed that scaling up to larger problems can be
accomplished by increasing the processing power
1969, Minsky and Papert: Perceptrons – a discouragement of
further research in neural networks

IAI –
1970 – 1979: Knowledge-based systems

DENDRAL, Fiegenbaum, Buchanan (Stanford) – a

knowledge based system performs reasoning about
molecular structures of organic compounds based on mass
spectroscopy – 450 rules
MYCIN, Shortliffe (Stanford), 550 rules, different from
DENDRAL: no theoretical model as a foundation, introduces
the “certainty factors”
Advances in natural language processing
PROLOG – logical programming language popular in
Europe 1975, Minsky: frame theory

IAI –
1980 –
2010

1980 – AI becomes an industry! (from several million

dollars in 1980 up to a billion dollars in 1988)
1982 McDermott – DEC R1 expert system
1980 – Comeback of neural networks (Werbos –
backpropagation
algorithms)
Intelligent agents (agent – perception of the
environment through sensors and acting on it through
actions)
Robotics
Machine
learning

IAI –
2010 – today
The era of deep learning
Deep learning – machine learning of multilayered data
abstractions Typically using neural networks on large
amounts of data
Stunning advances in computer vision, promising
improvements in natural language processing

IAI –