learning
DESCRIPTION
TRANSCRIPT
CS451/CS551/EE565ARTIFICIAL INTELLIGENCE
Learning & Connectionism
12-04-2006
Prof. Janice T. Searleman
[email protected], jetsza
Outline Learning Agents Neural Nets
Reading Assignment: AIMA Chapter 18, Learning from Observations
Chapter 19, sections 19.1, Logical Formulation of Learning
Chapter 20, section 20.5, Neural Networks
Final Exam: Mon, 12/11/06, 8:00 am, SC342HW#7 posted; due: Wed. 12/06/06
What is Learning? memorizing something learning facts through observation and
exploration improving motor and/or cognitive skills
through practice organizing new knowledge into general,
effective representations
Some types of learning Rote learning Reinforcement learning – an agent interacting
with the world makes observations, takes actions, and is rewarded or punished; it should learn to choose actions in such a way as to obtain a lot of reward
Supervised induction (with a teacher) – given a set of input/output pairs, find a rule that does a good job of predicting the output associated with a new input
Unsupervised induction Analogy (case-based) learning Evolutionary learning
LearningRote learning Samuel’s checker program
… by taking advice FOO
… from problem-solving experience
STRIPS (Shakey)
… from examples & counterexamples
Winston’s concept learner
… by parameter adjustment Samuel’s checker program
… by chunking SOAR
… by analogy
… by discovery AM/EURISKO
Genetic learning
Connectionism (Neural Net)
Learning agents
Learning The idea behind learning is that percepts
should not only be used for acting now, but also for improving the agent’s ability to act in the future.
In the psychology literature, learning is considered one of the keys to human intelligence.
Learning element Design of a learning element is affected by
Which components of the performance element are to be learned
What feedback is available to learn these components
What representation is used for the components
Type of feedback:Supervised learning: correct answers for each
exampleUnsupervised learning: correct answers not
givenReinforcement learning: occasional rewards
Rote Learning This is the simplest form of learning. It involves nothing more than memorizing
experiences, e.g., sensor inputs, actions taken, rewards received.
It’s surprisingly effective!
Machine learning programs for classification (concept learning)
Assume you have a goal concept that you are trying to learn, called the target concept. Your guesses or approximations of the target concept are called hypotheses.An example target concept might be a
description of diseased soybean plants. An object (fact) which is used to help learn the goal
concept is called an instance or an example. It can also be called a case.
An instance/example x is described by a vector of features, also called attributes , i.e., x = <x1,……,xn>.
Classification tasks Many engineering and diagnosis tasks involve
classification or prediction, e.g., Parts inspection: classify parts into: defective or OK. Mammogram analysis: given a mammogram,
estimate the probability that is normal, pre-cancerous or cancerous.
Document understanding: given a rectangular region from a scanned region, classify it as text or graphics.
Soybean plant analysis: classify plants into: diseased or not diseased.
Machine learning programs for classification (concept learning) Given: A labeling function f that maps feature
vectors into a discrete set of k classes. That is, f(x) in {0,1,……,k-1}. Often, there are only 2 classes, called “positive” (+) and “negative” (-).
Represent each training example as a pair (x,f(x)). These are the examples that will be used for learning the concept.
Problem: From a set of (x,f(x)) pairs, learn the target concept f.
The learning problem Given <x,f(x)> pairs, infer f
x f(x)
1 1
2 4
3 9
4 16
5 ?
Given a finite sample, it is often impossible to guess the truefunction f.
Approach: Find some pattern (called a hypothesis) inthe training examples, and assumethat the pattern will hold for futureexamples too.
Hypothesis or model selection What class of hypotheses (models) should we consider?
Assume f is a set of rules. Then the space of hypotheses consists of rule sets.
Assume f is a simple polynomial. Then the space of hypotheses consists of simple polynomials. Regression could be used to learn f.
Assume f can be expressed as a decision tree. Then the space of hypotheses consists of decision trees. Decision tree learning can be applied.
Assume f can be expressed as a neural network. Then the space of hypotheses consists of neural nets, and backprop can be used to learn the weights.
Let H be the space of all possible hypotheses H that a learning program considers. Then the learner seeks the H in H that “fits” the given data the “best.” This is a process of search through the space of possible hypotheses in H.
Learning decision treesProblem: decide whether to wait for a table at a restaurant,
based on the following attributes:1. Alternate: is there an alternative restaurant nearby?2. Bar: is there a comfortable bar area to wait in?3. Fri/Sat: is today Friday or Saturday?4. Hungry: are we hungry?5. Patrons: number of people in the restaurant (None,
Some, Full)6. Price: price range ($, $$, $$$)7. Raining: is it raining outside?8. Reservation: have we made a reservation?9. Type: kind of restaurant (French, Italian, Thai, Burger)10. WaitEstimate: estimated waiting time (0-10, 10-30, 30-
60, >60)
Attribute-based representations Examples described by attribute values (Boolean, discrete,
continuous) E.g., situations where I will/won't wait for a table:
Classification of examples is positive (T) or negative (F)
Connectionism
Recall: Physical Symbol System A physical symbol system is a machine that
produces through time an evolving collection of symbol structures. Such a system exists in a world of objects wider than just these symbolic expressions themselves.
The Physical Symbol System Hypothesis A physical symbol system has the necessary and
sufficient means for general intelligent action.
PSS => Intelligence Well…maybe
Intelligence => PSS???
Symbols & The Main Goals of AI Engineering: Build intelligent systems
Lots of fantastic symbolic AI systems for a multitude of specialized tasks….and many more to come!
But general intelligent systems are a major problem, since common sense is hard to represent and reason with symbolically.
Science: Understand natural intelligence via computers Cognitive Science founded by symbolic AI researchers. But they took the metaphor too far.
Organisms clearly compute, but not necessarily: as Von Neumann computers (i.e. serially) as Logic theorem provers (i.e. mathematically
complete & consistent) with symbols!! …We can interpret the reasoning
process as symbolic, but the underlying mechanism may not be. The ends don’t explain the means!
The Intelligence Spectrum Robot (Moravec ,1999)
Calculate Sense & ActReason
ComputersHumans
■ On the fringes: Humans are slow, error-prone calculators Robots sense and act no better (and much slower) than frogs
■ The battle for middle ground: Deep Blue beat the best human chess player But minimax search ≠ “reasoning”.
GOFAI -vs- The New AICalc Sense & ActReason
GOFAI
New AI
GOFAI■ Disembodied reasoning systems can’t plug-and-play on robots. ■ Lack of common sense => no general human reasoning abilities.
New AI■ Embodied S&A gives basis for common sense but has not yet
scaled up to sophisticated human-like abstract reasoning.
(“Good Old Fashioned AI)
Evolutionary Progressions along the Intelligence Spectrum
Evolution of reasoning was tightly constrained and influenced by sensorimotor capabilities. Else extinction!
GOFAI systems are often in their own little worlds, making unreasonable assumptions about independent sensorimotor apparatus.
To achieve AI’s scientific goal of understanding human intelligence, the road from sense-and-act to reasoning via simulated evolution may be the only way.
But, to achieve AI’s engineering goals, both approaches seem important.
Living organisms Computers
Sense & Act: 10,000,000+ years. 15+ years
Reason: 100,000+ 30+ years
Calculate 1,000+ 50+ years
The Situated & Embodied AI Hypothesis
Complex intelligence is better understood and more successfully embodied in artifacts by working up from low-level sensory-motor agents than from abstract cognitive mechanisms of rationality (e.g. logic, means-ends analysis, etc.).
Cognitive Incrementalism: Cognition (and hence common sense) is an extension of sensorimotor behavior.
Brooks, Steels, Pfeifer, Scheier, Beer, Nolfi, Floreano…
The Artificial Life Approach to AI
2 2 2 2 2 2 2 2 2 1 7 0 1 4 0 1 4 22 0 2 2 2 2 2 2 0 22 7 2 2 1 22 1 2 2 1 22 0 2 2 1 22 7 2 2 1 22 1 2 2 2 2 2 2 1 2 2 2 2 22 0 7 1 0 7 1 0 7 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2
Langton Loop
Cellular Automata
Simulated Real Worlds
Simple Robots
■ Synthetic: Bottom-up, multiple interacting agents■ Self-Organizing: Global structure is emergent. ■ Self-Regulating: No global/centralized control.■ Adaptive: Learning and/or evolving■ Complex: On the edge of chaos; dissipative
Adaptation Key focus of Situated & Embodied AI (i.e., Alife AI)
But now, often at level of simple organisms (ants, flies, frogs, etc.)
Machine Learning (ML) is also a key part of GOFAI. Alife AI is very interested in subsymbolic ML
techniques:Artificial Neural Networks (ANNs)Evolutionary Algorithms (EAs)
Learning: agents modify their own behavior (normally to improve performance) in their lifetime.
Evolution: populations of agents change their behavior over the course of many generations.
Both: Evolving populations of learning agents
Neural Networks Also ‘connectionism’, ‘Parallel Distributed
Processing’, ‘subsymbolic AI’ AI technique Analogous to processes in the brain “Intelligence emerges from the interactions
of large numbers of simple processing units” (Rumelhart et al., 1986)
Roughly based on brains – some simplification is made
Real Neuron
from Searleman & Searleman, Introduction to Cognition
Two interacting neurons
Excitatory (E) and Inhibitory (I) impulses(from Searleman & Searleman, Introduction to Cognition)
NeuroPhysiology
Axon Dendrites
SynapsesNeurons
• Dense: Human brain has 1011 neurons, 1014 synapses• Highly Interconnected: Human neurons have 104 fan-in.• Neurons firing: send action potentials (APs) down the axons when sufficiently stimulated by SUM of incoming APs along the dendrites.
• Neurons can either stimulate or inhibit other neurons.
• Synapses vary in transmission efficiency
Features of the human brain Robust – fault tolerant and degrade
gracefully Flexible -- can learn without being
explicitly programmed Can deal with fuzzy, probabilistic
information Is highly parallel
Connectionist models Key intuition: Much of intelligence is in the connections
between the 10 billion neurons in the human brain. Neuron switching time is roughly 0.001 second; scene
recognition time is about 0.1 second. This suggests that the brain is massively parallel because 100 computational steps are simply not sufficient to accomplish scene recognition.
Development: Formation of basic connection topology Learning: Fine-tuning of topology + Major synaptic-
efficiency changes.
The matrix IS the intelligence!