This document provides information about an artificial intelligence course, including the instructor, grading breakdown, schedule, and topics. Some key areas of AI discussed are search techniques, constraint satisfaction problems, game playing, logic, classification, and intelligent agents. The history and current state of the art in AI are also reviewed, covering successes in robotics, speech recognition, planning, and other domains.
Artificial Intelligent introduction or historyArslan Sattar
- Begging for small things can become a habit over time as one comes to rely on getting others to provide even minor things.
- It is better to be self-sufficient as much as possible and only ask for help when truly needed, to avoid forming a dependent mindset.
- Developing independence over small matters builds confidence and strength of character.
This document provides an overview of artificial intelligence including:
- It defines four approaches to AI: acting humanly through the Turing test, thinking humanly through cognitive modeling, thinking rationally through symbolic logic, and acting rationally as intelligent agents.
- It then summarizes the history of AI from its origins in the 1940s through developments in knowledge-based systems, connectionism, and the emergence of intelligent agents using large datasets.
- Finally, it briefly discusses recent applications of AI such as algorithms used by Facebook, TikTok, and noise cancellation in Zoom calls.
This document provides an overview of an introductory artificial intelligence course. It describes the course topics which include search, logic, probability, and learning techniques. It also summarizes the current state of AI, highlighting successes in logistics, games, natural language processing, vision, robotics, and question answering. The course is intended for juniors and seniors and requires programming skills and exposure to algorithms, calculus, and probability.
The document discusses artificial intelligence and provides information on various AI topics. It includes a list of 9 NPTEL video links on topics related to unit 1 of an AI course, learning outcomes of the course, definitions and descriptions of AI, areas and applications of AI, a brief history of AI, task domains and techniques in AI, and examples of search problems and search methods. Depth-first search is described as a method that exhaustively explores branches in a search tree to the maximum depth until a solution is found.
This document provides an overview of an introductory course on artificial intelligence. It discusses four views of AI: thinking humanly, thinking rationally, acting humanly, and acting rationally. The textbook advocates the view of "acting rationally" by designing agents that maximize goal achievement given available information. A brief history of AI is also provided, from early work in philosophy, mathematics, and the sciences to landmark developments like Turing's 1950 paper posing the question "Can machines think?". The state of the art in AI is summarized with examples like Deep Blue defeating Kasparov at chess in 1997 and autonomous vehicles driving 98% of the time across the US.
This document provides an overview of the CSC384 Intro to Artificial Intelligence course. It discusses what AI is, including modeling intelligence through computation. It describes different approaches like mimicking humans versus achieving rational behavior. The document outlines key topics that will be covered in the course like search, knowledge representation, planning and probabilistic reasoning. It also provides examples of successes in AI and discusses degrees of intelligence in systems.
This document provides an overview of an introduction to artificial intelligence course. It discusses course administration details like the instructor, TAs, meeting times, grading, and textbook. It then covers topics that will be discussed in the course like what AI is, the ingredients of intelligence, history of AI, applications of AI, and goals of AI. Key problems in AI like representation, search, inference, learning, and planning are also summarized. Different design methodologies like thinking rationally to formalize inference and thinking like humans from a cognitive science perspective are contrasted.
Here are the steps I would take to diagnose electrical problems with a car:
1. Check the spark plugs. Look for fouling, cracking, or gaps that are too wide or narrow. Replace as needed.
2. Check the ignition timing. Use a timing light to ensure it is properly set. Adjust if necessary.
3. Test the battery with a voltmeter. It should read over 12 volts. If lower, have the battery and charging system checked.
4. Inspect wires and connectors for cracks, corrosion or loose connections. Tighten or replace as needed.
5. Check for faulty sensors that could cause ignition or fuel delivery problems, like the crankshaft position sensor
Here are the steps I would take to diagnose electrical problems with a car:
1. Check the spark plugs. Look for fouling, cracking, or gaps that are too wide or narrow. Replace as needed.
2. Check the ignition timing. Use a timing light to ensure it is properly set. Adjust if necessary.
3. Test the battery with a voltmeter. It should read over 12 volts. If lower, have the battery and charging system inspected.
4. Inspect wires and connectors for cracks, corrosion or loose connections. Tighten or replace as needed.
5. Check for faulty sensors that could cause ignition or fuel delivery issues, like the crankshaft position sensor
computer science engineering spe ialized in artificial IntelligenceKhanKhaja1
Dr. C. Lee Giles is a professor at Penn State University who teaches a course on artificial intelligence and information sciences. The document provides an overview of artificial intelligence including definitions, theories, impact on information science, and topics covered in the course such as machine learning, information retrieval, text processing, and social networks. It also discusses the scientific method applied to developing theories in information sciences and contrasts weak and strong definitions of artificial intelligence.
Here are the steps I would take to diagnose electrical problems with a car:
1. Check the spark plugs. Look for fouling, cracking, or gaps that are too wide or narrow. Replace as needed.
2. Check the ignition timing. Use a timing light to ensure it is properly set. Adjust if necessary.
3. Test the battery with a voltmeter. It should read over 12 volts. If lower, have the battery and charging system inspected.
4. Inspect wires and connectors for cracks, corrosion or loose connections. Tighten or replace as needed.
5. Check for faulty sensors that could cause ignition or fuel delivery issues, like the crankshaft position sensor
Dr. C. Lee Giles is a professor at Penn State University who teaches a course on artificial intelligence and information sciences. The document provides an overview of artificial intelligence including definitions, theories, impact on information science, and topics covered in the course such as machine learning, information retrieval, text processing, and social networks. It also discusses the scientific method applied to developing theories in information sciences and contrasts weak and strong definitions of artificial intelligence.
Here are the steps I would take to diagnose electrical problems with a car:
1. Check the spark plugs. Look for fouling, cracking, or gaps that are too wide or narrow. Replace as needed.
2. Check the ignition timing. Use a timing light to ensure it is properly set. Adjust if necessary.
3. Test the battery with a voltmeter. It should read over 12 volts. If lower, have the battery and charging system inspected.
4. Inspect wires and connectors for cracks, corrosion or loose connections. Tighten or replace as needed.
5. Check for faulty sensors that could cause ignition or fuel delivery issues, like the crankshaft position sensor
This document provides an overview of an artificial intelligence course, including:
1) Course mechanics like assignments, quizzes, and policies on cheating.
2) Today's lecture will cover the goals of AI, a brief history, the current state of the art, and three key ideas: search, representation/modeling, and learning.
3) Questions are posed about how to measure intelligence and which tasks, like chess or picking up eggs, are more difficult for robots.
This document provides an overview of artificial intelligence. It defines intelligence as the ability to plan, solve problems, reason, learn, understand new situations, and apply knowledge. AI is described as building intelligent systems that can think and act like humans or rationally. The history of AI is discussed, from its origins in the 1950s to current applications. Key concepts to be learned in the semester include problem solving, machine learning, evolutionary computation, robotics, and intelligent agents. Python and NetLogo will be used as tools.
The document provides an introduction to artificial intelligence, including definitions of AI, a brief history of the field, and the current state of the art. It discusses four views of AI: thinking humanly, thinking rationally, acting humanly, and acting rationally. The textbook advocates the view of "acting rationally" by designing agents that perceive and act to maximize goals. The document also outlines some of the key topics that will be covered in the course, including search, logic, planning, and learning.
- The document discusses artificial intelligence, including its history, key areas such as knowledge representation and learning, and applications in areas like consumer marketing, identification technologies, predicting stock markets, and machine translation.
- While progress has been made in areas like recognition and learning, challenges remain in full natural language understanding, human-level planning and decision making. AI is being applied across many industries but remains an active area of research.
Artificial intelligence (AI) is concerned with designing intelligent systems, with two key aspects - intelligence and an artificial device. There are different views on what constitutes intelligence - emulating human thought processes, passing the Turing test of indistinguishability from humans, focusing on logical reasoning abilities, or acting rationally to achieve goals. AI research involves problems like perception, reasoning, learning, language understanding, problem-solving and robotics. While today's AI can achieve limited success in tasks like computer vision, robotics, translation and games, it still cannot match human-level abilities in areas like language understanding, planning, learning or exhibiting true autonomy. The history of AI began in the 1950s and has progressed through periods focused on games
Introduction to Artificial Intelligence.pdfgqgy2nsf5x
Artificial intelligence (AI) is the study of intelligent agents that act rationally to maximize their chances of success. The document discusses several key aspects of AI including definitions, goals, foundations, topics, history and applications. Some of the major topics in AI are search, knowledge representation and reasoning, planning, learning, natural language processing, expert systems, and interacting with the environment through vision, speech recognition and robotics.
This document provides information about the COMPSCI 270: Artificial Intelligence course at Duke University. The course will be taught in the spring of 2019 by Professor Vincent Conitzer. It will cover topics such as search, constraint satisfaction, game playing, logic, knowledge representation, and planning. Assignments will count for 30% of the grade, midterms for 40%, and a final exam for 30%. The course assumes some programming experience and background in algorithms, probability, and discrete mathematics. It aims to cover general AI techniques applied to tasks like solving Rubik's cubes, scheduling meetings, and playing games like chess.
A NICER VIEW OF THE NEAREST AND BRIGHTEST MILLISECOND PULSAR: PSR J0437−4715Sérgio Sacani
We report Bayesian inference of the mass, radius and hot X-ray emitting region properties - using data
from the Neutron Star Interior Composition ExploreR (NICER) - for the brightest rotation-powered
millisecond X-ray pulsar PSR J0437−4715. Our modeling is conditional on informative tight priors
on mass, distance and binary inclination obtained from radio pulsar timing using the Parkes Pulsar
Timing Array (PPTA) (Reardon et al. 2024), and we use NICER background models to constrain
the non-source background, cross-checking with data from XMM-Newton. We assume two distinct
hot emitting regions, and various parameterized hot region geometries that are defined in terms of
overlapping circles; while simplified, these capture many of the possibilities suggested by detailed
modeling of return current heating. For the preferred model identified by our analysis we infer a mass
of M = 1.418 ± 0.037 M⊙ (largely informed by the PPTA mass prior) and an equatorial radius of
R = 11.36+0.95
−0.63 km, each reported as the posterior credible interval bounded by the 16% and 84%
quantiles. This radius favors softer dense matter equations of state and is highly consistent with
constraints derived from gravitational wave measurements of neutron star binary mergers. The hot
regions are inferred to be non-antipodal, and hence inconsistent with a pure centered dipole magnetic
field.
The CGIAR needs a revolution John McIntire a, Achim Dobermann bAbdellah HAMMA
The CGIAR is a unique scientific organization that seeks to improve food security for low-income people. It
should be leading efforts to generate sustainable productivity gains in agriculture, especially in sub-Saharan
Africa where productivity lags. However, its current ill-adapted priorities and structure, its obsession with reorganizations,
and its unproductive ventures into local development projects have reduced its impact and
rendered it unable to respond to the challenge of food security under climate change. The system’s efforts have
become too diffuse and ineffective while attempts to revive impact through repeated re-organizations have
failed. The CGIAR has unique strengths: access to plant germplasm, know-how to improve germplasm and
agronomic practices, global networks of experimental sites and research collaborators, and excellent staff. The
CGIAR’s scientists are highly motivated, but leaders and funders of the system have failed to support them with a
simple, focused, and better funded operational environment needed to succeed in their research – and have
greater impact from it. This can be corrected. We propose a scientific and problem-driven focus on fewer global
and regional research priorities, supported by adequate long-term funding, rigorous methods of project evaluation,
and management that stimulates innovation and seeks verifiable results. These supports do not exist today
and we do not see that the current One CGIAR system will provide them in the foreseeable future.
Simulations of pulsed overpressure jets: formation of bellows and ripples in ...Sérgio Sacani
Jets from active nuclei may supply the heating which moderates cooling and accretion from the circum-galactic medium. While
steady overpressured jets can drive a circulatory flow, lateral energy transfer rarely exceeds 3 per cent of jet power, after the initial
bow shock has advanced. Here, we explore if pulses in high-pressure jets are capable of sufficient lateral energy transfer into
the surrounding environment. We answer this by performing a systematic survey of numerical simulations in an axisymmetric
hydrodynamic mode. Velocity pulses along low Mach jets are studied at various overpressures. We consider combinations of
jet velocity pulse amplitude and frequency. We find three flow types corresponding to slow, intermediate, and fast pulsations.
Rapid pulsations in light jets generate a series of travelling shocks in the jet. They also create ripples which propagate into the
ambient medium while a slow convection flow brings in ambient gas which is expelled along the jet direction. Long period pulses
produce slowly evolving patterns which have little external effect, while screeching persists as in non-pulsed jets. In addition,
rapid pulses in jets denser than the ambient medium generate a novel breathing cavity analogous to a lung. Intermediate period
pulses generate a series of bows via a bellows action which transfer energy into the ambient gas, reaching power efficiencies of
over 30 per cent when the jet overpressure issufficiently large. This may adequately inhibit galaxy gas accretion. In addition,such
pulses enhance the axial out-flow of jet material, potentially polluting the circum-galactic gas with metal-enriched interstellar
gas.
Presentation consists of theories of shoot apical meristem and different type of shoot apex organization in Pteridophytes, Gymnosperms and Angiosperms.
From Seeds to Supermassive Black Holes: Capture, Growth, Migration, and Pairi...Sérgio Sacani
The origins and mergers of supermassive black holes (SMBHs) remain a mystery. We describe a scenario from a
novel multiphysics simulation featuring rapid (1 Myr) hyper-Eddington gas capture by a ∼1000 Me “seed” black
hole (BH) up to supermassive (106 Me) masses in a massive, dense molecular cloud complex typical of highredshift starbursts. Due to the high cloud density, stellar feedback is inefficient, and most of the gas turns into stars
in star clusters that rapidly merge hierarchically, creating deep potential wells. Relatively low-mass BH seeds at
random positions can be “captured” by merging subclusters and migrate to the center in ∼1 freefall time (vastly
faster than dynamical friction). This also efficiently produces a paired BH binary with ∼0.1 pc separation. The
centrally concentrated stellar density profile (akin to a “protobulge”) allows the cluster as a whole to capture and
retain gas and build up a large (parsec-scale) circumbinary accretion disk with gas coherently funneled to the
central BH (even when the BH radius of influence is small). The disk is “hypermagnetized” and “flux-frozen”:
dominated by a toroidal magnetic field with plasma β ∼ 10−3
, with the fields amplified by flux-freezing. This
drives hyper-Eddington inflow rates 1 Me yr−1
, which also drive the two BHs to nearly equal masses. The latestage system appears remarkably similar to recently observed high-redshift “little red dots.” This scenario can
provide an explanation for rapid SMBH formation, growth, and mergers in high-redshift galaxies.
How Does Simulation-Based Testing for Self-Driving Cars Match Human Perception?Christian Birchler
Software metrics such as coverage or mutation scores have been investigated for the automated quality assessment of test suites. While traditional tools rely on software metrics, the field of self-driving cars (SDCs) has primarily focused on simulation-based test case generation using quality metrics such as the out-of-bound (OOB) parameter to determine if a test case fails or passes. However, it remains unclear to what extent this quality metric aligns with the human perception of the safety and realism of SDCs. To address this (reality) gap, we conducted an empirical study involving 50 participants to investigate the factors that determine how humans perceive SDC test cases as safe, unsafe, realistic, or unrealistic. To this aim, we developed a framework leveraging virtual reality (VR) technologies, called SDC-Alabaster, to immerse the study participants into the virtual environment of SDC simulators. Our findings indicate that the human assessment of safety and realism of failing/passing test cases can vary based on different factors, such as the test’s complexity and the possibility of interacting with the SDC. Especially for the assessment of realism, the participants’ age leads to a different perception. This study highlights the need for more research on simulation testing quality metrics and the importance of human perception in evaluating SDCs.
Synopsis: Analysis of a Metallic SpecimenSérgio Sacani
The All-Domain Anomaly Resolution Office (AARO) sponsored a series of measurements on a layered material
specimen primarily composed of magnesium and zinc, with bands of bismuth and other co-located trace elements.
The material specimen, whose origin and purpose are of long and debated history, is claimed to be recovered
from an unidentified anomalous phenomenon (UAP) crash in or around 1947. Furthermore, the specimen’s
physiochemical properties are claimed to make the material capable of “inertial mass reduction” (i.e., levitation or
antigravity functionality), possibly attributable to the material’s bismuth and magnesium layers acting as a terahertz
waveguide
This pdf is about the introduction to concept of Balanced Diet & Nutrients.
For more details visit on YouTube; @SELF-EXPLANATORY; https://www.youtube.com/channel/UCAiarMZDNhe1A3Rnpr_WkzA/videos
Thanks...!
Complementary interstellar detections from the heliotailSérgio Sacani
The heliosphere is a protective shield around the solar system created by the Sun’s interaction with the local interstellar medium (LISM) through the solar wind, transients, and interplanetary magnetic field. The shape of the heliosphere is directly linked with interactions with the surrounding LISM, in turn affecting the space environment within the heliosphere. Understanding the shape of the heliosphere, the LISM properties, and their interactions is critical for understanding the impacts within the solar system and for understanding other astrospheres. Understanding the shape of the heliosphere requires an understanding of the heliotail, as the shape is highly dependent upon the heliotail and its LISM interactions. The heliotail additionally presents an opportunity for more direct in situ measurement of interstellar particles from within the heliosphere, given the likelihood of magnetic reconnection and turbulent mixing between the LISM and the heliotail. Measurements in the heliotail should be made of pickup ions, energetic neutral atoms, low energy neutrals, and cosmic rays, as well as interstellar ions that may be injected into the heliosphere through processes such as magnetic reconnection, which can create a direct magnetic link from the LISM into the heliosphere. The Interstellar Probe mission is an ideal opportunity for measurement either along a trajectory passing through the heliotail, via the flank, or by use of a pair of spacecraft that explore the heliosphere both tailward and noseward to yield a more complete picture of the shape of the heliosphere and to help us better understand its interactions with the LISM.
atom, elements, molecule and compounds #CBSE, #IX class, #chapter-3, #ATOMS&M...ManjulaVani3
#cbseclass-9th, #atomsand molecules, #Classification, of Matter
Matter can be classified into pure substances and mixtures:
Pure Substances
Elements: Consist of only one type of atom (e.g., Iron (Fe), Nitrogen (N2)).
Compounds: Consist of two or more types of atoms chemically bonded in a fixed ratio (e.g., Water (H2O), Carbon dioxide (CO2)).
Mixtures
Homogeneous Mixtures (Solutions): Uniform composition throughout (e.g., Saltwater, Air).
Heterogeneous Mixtures: Non-uniform composition, components are distinguishable (e.g., Salad, Sand and iron filings).
Atom
Definition: The smallest unit of matter that retains the identity of a chemical element. Example: A single helium atom.Element
Definition: A pure substance consisting of only one type of atom, distinguished by its atomic number (the number of protons in the nucleus).Example: Oxygen (02)Molecule
Definition: Two or more atoms chemically bonded together. Molecules can consist of atoms of the same element or different elements.
Types:
Diatomic Molecules: Two atoms, either of the same element (e.g., 02)or different elements (e.g.,
CO).
Polyatomic Molecules: More than two atoms
Example: Water (H2O), Carbon dioxide (CO2). Compound
Definition: A substance formed when two or more different types of atoms chemically bond in a fixed ratio.
Properties: Compounds have properties different from their constituent elements.
Example: Sodium chloride (NaCl), Glucose (C6H12O6).
•
The main #types, of #chemical, #reactions,ManjulaVani3
Chemical reactions can be classified into several main types based on the changes that occur during the reaction. Here are the main types:
1. Synthesis (Combination) Reactions
Definition: Two or more reactants combine to form a single product.
General Form:
𝐴
+
𝐵
→
𝐴
𝐵
A+B→AB
Example:
2
𝐻
2
+
𝑂
2
→
2
𝐻
2
𝑂
2H
2
+O
2
→2H
2
O (formation of water)
2. Decomposition Reactions
Definition: A single compound breaks down into two or more simpler substances.
General Form:
𝐴
𝐵
→
𝐴
+
𝐵
AB→A+B
Example:
2
𝐻
2
𝑂
2
→
2
𝐻
2
𝑂
+
𝑂
2
2H
2
O
2
→2H
2
O+O
2
(decomposition of hydrogen peroxide)
3. Single Displacement (Single Replacement) Reactions
Definition: One element replaces another element in a compound.
General Form:
𝐴
+
𝐵
𝐶
→
𝐴
𝐶
+
𝐵
A+BC→AC+B
Example:
𝑍
𝑛
+
2
𝐻
𝐶
𝑙
→
𝑍
𝑛
𝐶
𝑙
2
+
𝐻
2
Zn+2HCl→ZnCl
2
+H
2
(zinc displacing hydrogen in hydrochloric acid)
4. Double Displacement (Double Replacement) Reactions
Definition: The ions of two compounds exchange places in an aqueous solution to form two new compounds.
General Form:
𝐴
𝐵
+
𝐶
𝐷
→
𝐴
𝐷
+
𝐶
𝐵
AB+CD→AD+CB
Example:
𝐴
𝑔
𝑁
𝑂
3
+
𝑁
𝑎
𝐶
𝑙
→
𝐴
𝑔
𝐶
𝑙
+
𝑁
𝑎
𝑁
𝑂
3
AgNO
3
+NaCl→AgCl+NaNO
3
(reaction between silver nitrate and sodium chloride)
5. Combustion Reactions
Definition: A substance combines with oxygen, releasing energy in the form of light and heat.
General Form:
𝐶
𝑥
𝐻
𝑦
+
𝑂
2
→
𝐶
𝑂
2
+
𝐻
2
𝑂
C
x
H
y
+O
2
→CO
2
+H
2
O (for hydrocarbons)
Example:
𝐶
𝐻
4
+
2
𝑂
2
→
𝐶
𝑂
2
+
2
𝐻
2
𝑂
CH
4
+2O
2
→CO
2
+2H
2
O (combustion of methane)
6. Redox (Oxidation-Reduction) Reactions
Definition: Reactions that involve the transfer of electrons between reactants, resulting in changes in oxidation states.
General Form: Not fixed, but involves changes in oxidation numbers.
Example:
2
𝑁
𝑎
+
𝐶
𝑙
2
→
2
𝑁
𝑎
𝐶
𝑙
2Na+Cl
2
→2NaCl (sodium is oxidized and chlorine is reduced)
7. Acid-Base Reactions (Neutralization)
Definition: An acid reacts with a base to produce a salt and water.
General Form:
𝐻
𝐴
+
𝐵
𝑂
𝐻
→
𝐵
𝐴
+
𝐻
2
𝑂
HA+BOH→BA+H
2
O
Example:
𝐻
𝐶
𝑙
+
𝑁
𝑎
𝑂
𝐻
→
𝑁
𝑎
𝐶
𝑙
+
𝐻
2
𝑂
HCl+NaOH→NaCl+H
2
O (reaction between hydrochloric acid and sodium hydroxide)
Summary
These are the main types of chemical reactions, each characterized by specific changes in reactants and products. Understanding these types helps in predicting the outcomes of reactions and in balancing chemical equations.
Dalton's atomic theory july 2/2024 https://studio.youtube.com/video/922QQcaIoD8/edit
how to balance chemical equations jan4/2024 https://studio.youtube.com/video/qYV2UKnetAc/edit
the main types of chemical reactions dec16/2023 https://studio.youtube.com/video/zpKbiuWvfUE/edit
naming of alkanes dec8/2023 https://studio.youtube.com/video/d3fYwsIeyAM/edit
Dr Steffi Friedrichs from AcumenIST SRL presented the MACRAMÉ (www.MACRAME-Project.eu), CHIASMA (www.CHIASMA-Project-eu), INSIGHT (www.INSIGHT-Project.org) and PINK (www.PINK-Project.eu) Projects at this year;s Behoerdenklausur in Berlin.
3. Grading
• Grade Distribution
– Midterm 1 - 20
– Midterm 2 – 20
– Project – 20
– Final Exam – 40
• Midterm 1 Date
– Mod 3/1/1435
• Midterm 2 Date
– Mod 3/3/1435
• Project
– Due in Last Week
4. Warning!!!
Any form of cheating is not tolerated and can result in getting an F
in the class
5. Important Notes
• No class next week - Week of Sep 8
• Tutorials may not be held on its scheduled time
• We may have lectures on the tutorial sessions
or tutorials on lecture sessions
6. AI in Fiction
An intelligent killing robot
Smart machines that took over
the human race and made
them live in a simulated world
7. What’s interesting with AI
Search engines
Labor
Science
Medicine/
Diagnosis
Appliances
slide mostly borrowed from Laurent Itti
Movies Recommendation
8. What’s interesting with AI
• Honda AISMO
• Advanced Step in Innovation MObility
• Humanoid Robot
• Capable of recognizing:
• Moving objects
• Postures
• Gestures
• Handshake
• Sounds
• Capable of walking and running
http://en.wikipedia.org/wiki/ASIMO
9. What’s interesting with AI
Darpa Grand Challenge
• To nurture the development of autonomous ground vehicles
• Competition of Driverless vehicles
• 2004
• 1 million
• Mojave Desert
• Follows a route of 240 km
• No one won: best completed 12 km
• 2005
• 2 million dollar prize
• 3 narrow tunnels, 100 sharp turns
• Twisted pass with a drop-off one one side
• Five succeeded
• Winner: 6:54 hours, Stanford Racing Team – Stanely
Urban Grand Challenge
• 2007
• 2 million dollar
• AirForce Base
• To obey to all traffic rules
• 96 km within less than 6 hours
• CMU team won – with 4:10
http://en.wikipedia.org/wiki/DARPA_Grand_Challenge
stanely
10. What’s interesting with AI
• 1996, Deep Blue first machine to beat chess world champion
• But lost in the series – 4 to 2
• 1997, won the series 3.5 to 2.5
• Search 6 to 8 moves a head
• The evaluation function is set by the system after examining thousands of master
games
http://en.wikipedia.org/wiki/Deep_Blue_(chess_computer)
11. Syllabus - Tentative
1. Introduction (Chapter.1)
2. Intelligent Agents (Chapter.2)
3. Solving Problems by Search (Chapter.3 and chapter.4)
4. Constraint satisfaction Problems (Chapter.6).
5. Game Playing(Chapter.5)
6. Logical Agents (Chapter.7)
7. First Order Logic (Chapter.8)
8. Inference in logic (Chapter.9)
9. Classification
13. AI Definition
• The exciting new effort to make computers thinks …
machine with minds, in the full and literal sense”
(Haugeland 1985)
• The automation of activities that we associate with human
thinking, activities such as decision-making, problem
solving, learning,…(Bellman, 1978)
Think Like Humans
14. AI Defintion
• “The art of creating machines that perform functions that
require intelligence when performed by people” (Kurzweil,
1990)
• “The study of how to make computers do things at which, at
the moment, people do better”, (Rich and Knight, 1991)
Act Like Humans
15. AI Definition
• “The study of mental faculties through the use of
computational models”,(Charniak et al. 1985)
• “The study of the computations that make it possible to
perceive, reason and act”,(Winston, 1992)
Think Rationally
16. AI Definition
• “Computational Intelligence is the study of the design of
intelligent agents” (Poole et al, 1998)
• “AI….is concerned with intelligent behavior in artifact”,
(Nilsson, 1998)
Act Rationally
17. How to Achieve AI?
AI
Acting
humanly
Thinking
rationally
Acting
rationally
Thinking
humanly
17
18. Acting Humanly: The Turing Test
CSC 361 Artificial Intelligence 18
• To be intelligent, a program should simply act like a human
Alan Turing
1912-1954
http://en.wikipedia.org/wiki/Turing_test
19. The Turing Test - Example
http://www.ai.mit.edu/projects/infolab/
http://aimovie.warnerbros.com
slide mostly borrowed from Laurent Itti
20. The Turing Test - Example
http://www.ai.mit.edu/projects/infolab/
http://aimovie.warnerbros.com
slide mostly borrowed from Laurent Itti
21. The Turing Test - Example
http://www.ai.mit.edu/projects/infolab/
http://aimovie.warnerbros.com
slide mostly borrowed from Laurent Itti
22. The Turing Test - Example
http://www.ai.mit.edu/projects/infolab/
http://aimovie.warnerbros.com
slide mostly borrowed from Laurent Itti
23. The Turing Test - Example
http://www.ai.mit.edu/projects/infolab/
http://aimovie.warnerbros.com
slide mostly borrowed from Laurent Itti
24. Acting Humanly
24
• To pass the Turing test, the computer/robot needs:
– Natural language processing to communicate successfully.
– Knowledge representation to store what it knows or hears.
– Automated reasoning to answer questions and draw conclusions using
stored information.
– Machine learning to adapt to new circumstances and to detect and
extrapolate patterns.
– These are the main branches of AI.
25. Acting Humanly: The Turing Test
CSC 361 Artificial Intelligence 25
• To be intelligent, a program should simply act like a human
Alan Turing
1912-1954
http://en.wikipedia.org/wiki/Turing_test
+ physical interaction =>
Total Turing Test
- Recognize objects and
gestures
- Move objects
26. Acting Humanly – for Total Turing
• To pass the Turing test, the computer/robot needs:
– Natural language processing to communicate successfully.
– Knowledge representation to store what it knows or hears.
– Automated reasoning to answer questions and draw conclusions using stored
information.
– Machine learning to adapt to new circumstances and to detect and extrapolate
patterns.
– Computer vision to perceive objects. (Total Turing test)
– Robotics to manipulate objects and move. (Total Turing test)
– These are the main branches of AI.
27. Thinking Humanly
27
• Real intelligence requires thinking think like a
human !
• First, we should know how a human think
– Introspect ones thoughts
– Physiological experiment to understand how someone
thinks
– Brain imaging – MRI…
• Then, we can build programs and models that
think like humans
– Resulted in the field of cognitive science: a merger
between AI and psychology.
28. Problems with Imitating Humans
28
• The human thinking process is difficult to
understand: how does the mind raises from
the brain ? Think also about unconscious tasks
such as vision and speech understanding.
• Humans are not perfect ! We make a lot of
systemic mistakes:
29. Thinking Rationally
29
• Instead of thinking like a human : think rationally.
• Find out how correct thinking must proceed: the laws
of thought.
• Aristotle syllogism: “Socrates is a man; all men are
mortal, therefore Socrates is mortal.”
• This initiated logic: a traditional and important branch
of mathematics and computer science.
• Problem: it is not always possible to model thought as
a set of rules; sometimes there uncertainty.
• Even when a modeling is available, the complexity of
the problem may be too large to allow for a solution.
30. Acting Rationally
30
• Rational agent: acts as to achieve the best outcome
• Logical thinking is only one aspect of appropriate behavior:
reactions like getting your hand out of a hot place is not the
result of a careful deliberation, yet it is clearly rational.
• Sometimes there is no correct way to do, yet something
must be done.
• Instead of insisting on how the program should think, we
insist on how the program should act: we care only about
the final result.
• Advantages:
– more general than “thinking rationally” and more
– Mathematically principled; proven to achieve rationality unlike
human behavior or thought
31. Acting Rationally
31
This is how birds fly Humans tried to mimic
birds for centuries
This is how we finally
achieved “artificial flight”
32. Relations to Other Fields
CSC 361 Artificial Intelligence 32
• Philosophy
– Logic, methods of reasoning and rationality.
• Mathematics
– Formal representation and proof, algorithms, computation, (un)decidability, (in)tractability,
probability.
• Economics
– utility, decision theory (decide under uncertainty)
• Neuroscience
– neurons as information processing units.
• Psychology/Cognitive Science
– how do people behave, perceive, process information, represent knowledge.
• Computer engineering
– building fast computers
• Control theory
– design systems that maximize an objective function over time
• Linguistics
– knowledge representation, grammar
slide mostly borrowed from Max Welling
33. AI History
• Gestation of AI (1934 - 1955)
– In 1943, proposed a binary-based model of neurons
– Any computable function can be modeled by a set of neurons
– A serious attempt to model brain
– 1950, Turing’s “Computing Machinery and Intelligence ”: turing test,
reinforcement learning and machine learning
• The Inception of AI (1956)
– Dartmouth meeting to study AI
– an AI program ”Logic Theorist” to prove many theorems
• Early Enthusiasm and great Expectation (1952-1969)
– General Problem Solver imitates the human way of thinking
– LISP (AI programming language) was defined
– 1965, Robinson discovered the resolution method – logical reasoning
• AI Winter (1966-1973)
– Computational intractability of many AI problems
– Neural Network starts to disappear
34. AI History
• Knowledge-based systems (1969-1979)
– Use domain knowledge to allow for stronger reasoning
• Becomes an Industry (1980-now)
– Digital Equipment Corporation selling R1 “expert sytem”
– From few million to billions in 8 years
• The return of neural network (1986-now)
– With the back-propagation algorithm
• AI adopts scientific method (1987-now)
– More common to base theorems on pervious ones or rigorous evidence rather
than intuition
– Speech recognition and HMM
• Emergence of intelligent agent (1995-now)
– search engines, recommender systems,….
• Availability of very large data sets (2001 – now)
– Worry more about the data
35. The State of the Art
• Robotics Vehicle
– DARPA Challenge
• Speech Recognition
– United Airlines
• Autonomous Planning and Scheduling
– Remote Agent: Plan and control spacecraft
– MAPGEN: daily planning of operations on NASA’s exploration Rover
• Game Playing
– IBM Deep Blue
• Spam Fighting
• Logistic Planning
– DART – Dynamic Analysis and Replacing Tool
– Gulf War 1991
– To plan the logistic for transportation of 50k vehicles, cargo and people
– Generated in hour a plan that could take weeks
• Robotics
• Machine Translation
– Statistical models
36. Summary
CSC 361 Artificial Intelligence 36
• This course is concerned with creating rational agents:
artificial rationality.
• AI has passed the era of infancy and is now attacking real
life, complex problems, and it is succeeding in many of
them.
• The history of AI has had a turbulent history with many ups
and downs, phenomenal successes and deep
disappointments resulting in fund cutbacks and economic
losses.
• AI has flourished in the last two decades and it the
researchers mentality shifted towards a rigorous scientific
methodology:
Firm theoretical basis & Serious experiments