Sunteți pe pagina 1din 8

* Slide 1-14+ Backpropagation (BP) Algorithm

Perceptron

Change each weight by a small amount so as to reduce the total error

Backpropagation Algorithm Initialize each w to some small random value


i

Until the termination condition is met, Do

Multi-Layer Perceptrons (MLP) MLPs are feed-forward networks of simple processing units with at least ONE hidden layer. Each processing unit is similar to a perceptron, except for the threshold function which is replaced by a differentiable nonlinearity. The critical feature in MLPs is the non-linearity at the hidden layer. If all neurons in an MLP had a linear activation function, the MLP could be replaced by a single layer of perceptrons which can only solve linearly separable problems. Multilayer perceptrons (MLP)

XOR Problem

Multilayer Perceptron (MLP) Number of input neurons Number of hidden layers Number of hidden neurons Activation function

Backpropagation Algorithm The backpropagation algorithm trains a given feed-forward multilayer neural network for a given set of input patterns with known classifications. A Backpropagation neural network learns by example. You give the algorithm examples of what you want the network to do and it changes the networks weights so that, when training is finished, it will give you the required output for a particular input. Learning Rule Measure error: Mean-squared Error Reduce that error By appropriately adjusting each of the weights in the network BP algorithm is based on the error-correction learning rule. Training Time How many epochs of training? Stop if the error fails to improve (has reached a minimum) Stop if the rate of improvement drops below a certain level Stop if the error reaches an acceptable level Stop when a certain number of epochs have passed BP: General Procedure 1. Assign random values to the weights. 2. Present a pattern and target and calculate the error at the output layer 3. Estimate the error at the previous layer 4. Change all the weights a little bit to minimize the errors.

The backpropagation algorithm for a feedforward network (also called a multi-layer perceptron) Forward pass: for each pattern propagate activation from the input to the output Backward pass: Calculate the error at the output layer Propagate the error backwards through the network to estimate the contribution to the error from each unit

A genetic algorithm conceptually follows steps inspired by the biological processes of evolution. Genetic Algorithms follow the idea of SURVIVAL OF THE FITTEST- Better and better solutions evolve from previous generations until a near optimal solution is obtained. Also known as evolutionary algorithms, genetic algorithms demonstrate self organization and adaptation similar to the way that the fittest biological organism survive and reproduce. A genetic algorithm is an iterative procedure that represents its candidate solutions as strings of genes called chromosomes. Genetic Algorithm Based on Darwinian Paradigm

Intrinsically a robust search and optimization mechanism

GA Opera tors Selection replicates the most successful solutions found in a population at a rate proportional to their relative quality Recombination decomposes two distinct solutions and then randomly mixes their parts to form novel solutions Mutation randomly perturbs a candidate solution

Summary Neural network learning needs learning of weights from samples. Involves two steps: forward pass and the backward pass. Backpropagation is a general term for computing derivatives. [Slide 1-15] Genetic Algorithm Evolution Organisms (animals or plants) produce a number of offspring which are almost, but not entirely, like themselves Variation may be due to mutation (random changes) Variation may be due to sexual reproduction (offspring have some characteristics from each parent) Some of these offspring may survive to produce offspring of their ownsome wont The better adapted offspring are more likely to survive Over time, later generations become better and better adapted Genetic algorithms use this same process to evolve better programs Reproduction In asexual reproduction, Each organism (or solution) had only one parent Asexual reproduction is reproduction without sex The only way to introduce variation was through mutation (random changes) In sexual reproduction, Each organism (or solution) has two parents Assuming that each organism has just one chromosome, new offspring are produced by forming a new chromosome from parts of the chromosomes of each parent Genetic Algorithms A genetic algorithm (or short GA) is a search technique used in computing to find true or approximate solutions to optimization and search problems. Genetic algorithms are categorized as global search heuristics. Genetic algorithms are a particular class of evolutionary algorithms that use techniques inspired by evolutionary biology such as inheritance, mutation, selection, and recombination.

Many Variants of GA Different kinds of selection (not roulette) Tournament Elitism, etc. Different recombination Multi-point crossover 3 way crossover etc. Different kinds of encoding other than bitstring Integer values Real values Different kinds of mutation Advantages A GA has a number of advantages. It can quickly scan a vast solution set. Bad proposals do not effect the end solution negatively as they are simply discarded. This is very useful for complex or loosely defined problems. Disadvantages A practical disadvantage of the genetic algorithm involves longer running times on the computer. Fortunately, this disadvantage continues to be minimized by the ever-increasing processing speeds of today's computers. Genotypes and phenotypes Genes are the basic instructions for building an organism A chromosome is a sequence of genes Biologists distinguish between an organisms genotype (the genes and chromosomes) and its phenotype (what the organism actually is like) Example: You might have genes to be tall, but never grow to be tall for other reasons (such as poor diet) Similarly, genes may describe a possible solution to a problem, without actually being the solution Genetic Algorithms Representation of Candidate Solutions (CS) GAs on primarily two types of representations: Binary-Coded Real-Coded Binary-Coded GAs must decode a chromosome into a CS, evaluate the CS and return the resulting fitness back to the binary-coded chromosome representing the evaluated CS. The basic genetic algorithm Start with a large population of randomly generated attempted solutions to a problem

Repeatedly do the following: Evaluate each of the attempted solutions Keep a subset of these solutions (the best ones) Use these solutions to generate a new population Quit when you have a satisfactory solution (or you run out of time) It is started with a set of randomly generated solutions and recombine pairs of them at random to produce offspring. Only the best offspring and parents are kept to produce the next generation.

Selection: Roulette wheel

GA PROCEDURE We need the following Representation of an individual Fitness Function Reproduction Method Selection Criteria

Crossover Mimics biological recombination Some portion of genetic material is swapped between chromosomes Typically the swapping produces an offspring One-point crossover Randomly one position in the chromosomes is chosen Child 1 is head of chromosome of parent 1 with tail of chromosome of parent 2 Child 2 is head of 2 with tail of 1

Two-point crossover Randomly two positions in the chromosomes are chosen Avoids genes at the head and genes at the tail of a chromosome are always split when recombined

Encoding A data structure for representing candidate solutions Often takes the form of a bit string Usually has internal structure; i.e., different parts of the string represent different aspects of the solution) Design alternative individual (chromosome) Single design choice gene Design objectives fitness Selection: Roulette wheel In roulette wheel selection, the probability that individual i is selected, P(choice = i), is computed as follows

Uniform crossover A random mask is generated The mask determines which bits are copied from one parent and which from the other parent Bit density in mask determines how much material is taken from the other parent (takeover parameter)

Mutation Selects a random locus gene location with some probability and alters the allele (gene) at that locus. The intuitive mechanism for the preservation of variety in the population Generating new offspring from single parent Maintaining the diversity of the individuals Crossover can only explore the combinations of the current gene pool Mutation can generate new genes

Think of a roulette wheel in which the segments are of possibly different sizes, based on each individuals relative tness. Chance to be selected is exactly proportional to fitness

Fitness

A measure of the goodness of the organism. Expressed as the probability that the organism will live another cycle (generation) Basis for the natural selection simulation Organisms are selected to mate with probabilities proportional to their fitness. Probabilistically better solutions have a better chance of conferring their building blocks to the next generation (cycle)

GA Example: The Knapsack Problem Item: 1 2 3 4 5 6 7 Benefit: 5 8 3 2 7 9 4 Weight: 7 8 4 10 4 6 4 Knapsack holds a maximum of 22 pounds Fill it to get the maximum benefit Solutions take the form of a string of 1s and 0s Solutions: Also known as strings of genes called Chromosomes 1. 0101010 2. 1101100 3. 0100111 Example: The Knapsack Problem We represent a solution as a string of seven 1s and 0s and the fitness function as the total benefit, which is the sum of the gene values in a string solution times their representative benefit coefficient. The method generates a set of random solutions (initial parents), uses total benefit as the fitness function and selects the parents randomly to create generations of offspring by crossover and mutation. Knapsack Example Typically, a string of 1s and 0s can represent a solution. Possible solutions generated by the system using Reproduction, Crossover, or Mutations 1. 0101010 2. 1101100 3. 0100111 Knapsack example solution 1

*Slide 1-16+ Robotics


Origin of the word Robot" The word robot was first used more than 60 years ago by Karel Capek, a Czechoslovakian writer, in his play R.U.R., or Rossums Universal Robots. Robots revolt against their human masters a cautionary lesson now as then. He derived robot from the Czech word robota, which means drudgery or compulsory labor (forced labour ). Robots are machines which resemble people but work tirelessly. Robotics The word 'robotics' refers to the study and use of robots. The term was used by the Russian-born American scientist and writer Isaac Asimov. To be a robot a device must also have some degree of autonomy (the ability to carry on tasks self-sufficiently). Robots in the Media Robots have been presented in the media since the 1927 movie Metropolis. What is a Robot? A robot is a reprogrammable, multifunctional manipulator designed to move material, parts, tools, or specialized devices through variable programmed motions for the performance of a variety of tasks. (Robot Institute of America) A robot is a machine with sensors, processors, and effectors able to perceive the environment, have situational awareness, make appropriate decisions, and act upon the environment. An automatic device that performs functions normally ascribed to humans or a machine in the form of a human. Essential Characteristics of Robots Mobility: It possesses some form of mobility. Programmability: implying computational or symbolmanipulative capabilities that a designer can combine as desired (a robot is a computer). It can be programmed to accomplish a large variety of tasks. After being programmed, it operates automatically. Sensors: on or around the device that are able to sense the environment and give useful feedback to the device Mechanical capability: enabling it to act on its environment rather than merely function as a data processing or computational device (a robot is a machine); and Flexibility: it can operate using a range of programs and manipulates and transport materials in a variety of ways. Why build Robots? Humans have long dreamed about creating mechanical slaves that effortlessly carry out our daily tasks. Imagine being able to tell a robot to mow the lawn, or paint the fence, or entertain you, or drive you somewhere, or even teach you about something. Robot Classes Manipulators: robotic arms. These are most commonly found in industrial settings. Mobile Robots: unmanned vehicles capable of locomotion. Hybrid Robots: mobile robots with manipulators. How to the robots make decisions? Control is based on a set of behaviors. Each behavior has a set of preconditions that either Must be satisfied Are desired A behavior is selected when all of the musts become true. A behavior is selected from several behaviors based on how many desired conditions are true Robotics is AI-complete Robotics integrates many AI tasks Perception Vision, sound Reasoning Search, route planning, action planning Learning Recognition of objects/locations Exploration

Benefit 8 + 2 + 9 = 19 Weight 8 + 10 + 6 = 24 Knapsack Example Solution 2

Benefit 5 + 8 + 7 = 20 Weight 7 + 8 + 4 = 19 Knapsack Example Solution 3

Benefit 8 + 7 + 9 + 4 = 28 Weight 8 + 4 + 6 + 4 = 22 Solution 3 is clearly the best solution and has met our conditions, therefore, item number 2, 5, 6, and 7 will be taken on the hiking trip. We will be able to get the most benefit out of these items while still having weight equal to 22 pounds. This is a simple example illustrating a genetic algorithm approach. Conclusion Evolutionary algorithms have been around since the early sixties. They apply the rules of nature: evolution through selection of the fittest individuals The individuals representing solutions to a mathematical problem. Genetic algorithms are so far generally the best and most robust kind of evolutionary algorithms.

Rationale for Robots Three Hs: hot, heavy, hazardous Three Ds: dull, dirty, dangerous Ideal for the increasing lethality of warfare No casualties or POWs No high attrition of expensive manned systems Reduced public backlash Flexibility to counter terrorist,insurgent, and tribal warfare Increasing personnel costs & changing demographics Changing geopolitical climate & doctrine Proliferation of weapons of mass destruction (CBR) Render large areas toxic, uninhabitable Protective garments limit manned efficiency and effectiveness No need to encase and protect humans in vehicles: smaller, lighter, less expensive Expendable: suicide missions More survivable: small signature More maneuverable: faster, higher acceleration Faster response time: pre-positioning No casualties: riskier maneuvers and tactics Fearless and aggressive: not deterred by near misses Indefatigable: no need for sleep or rest Autonomous: fewer personnel can supervise more systems Advancing, emerging technology: advantage of strength and decreasing cost Disruptive, transformative technology: can counter new threats Swarm tactics Robot Components Body Actuators Controller Robot System Architecture

Robot::Controller Controllers direct a robot how to move. There are two controller paradigms Open-loop controllers execute robot movement without feedback. Closed-loop controllers execute robot movement and judge progress with sensors. They can thus compensate for errors. Robot::Software Architecture Control methods include deliberative methods and reactive methods. Deliberative methods are model-driven and involve planning before acting. Reactive methods is sensor-driven and behavior must emerge from interaction. Hybrid architectures are software architectures combining deliberative and reactive controllers. Emulating Human Attributes: Speech Synthesis Scientists must overcome some persistent barriers if they are to create competent humanoid robots. 1 Speech synthesis: the ability to get a robotic device to communicate using language. 2 Voice recognition: the ability to get a robot to understand us. Two seconds of speech may contain as much as 100,000 bits of data so it is extremely challenging to create computers powerful enough to process this amount of data. 3 Vision: the ability to get a robot to react as humans do to the physical environment using sophisticated vision systems. 4 Movement: the ability to get a robot to move around in the physical environment as humans can. Emulating Human Attributes: Speech Synthesis Speech synthesis is the artificial production of sounds resembling human speech. It will end our dependence on monitors and allow computers to speak to us. At present speech synthesis is being used to assist people who are speech-impaired. Words can be typed into a computer system and then the computer can be instructed to say these words. Blind people can use a special computer that can recognize letters in a book, then read the book aloud. However, more research and development is required to construct pleasant, human-sounding voices. Emulating Human Attributes: Voice Recognition Computers are able to listen, as demonstrated by Isolated Word Recognition (IWR). With IWR each word is surrounded by a silence gap so that word boundaries can be understood. Speakers train the system by recording words and sentences. IWR with a 1000 word vocabulary and 95 to 100% accuracy, running on personal computers is not uncommon. Interpreting continuous speech is considerably more difficult because continuous speech is not the same as a string of isolated words. Boundaries between words are not easily defined. Each persons voice is different. Background noise causes great difficulties.

Effectors Sensors Software

Robot::Body Typically defined as a graph of links and joints: A link is a part, a shape with physical properties. A joint is a constraint on the spatial relations of two or more links. Types of Joints Some Examples are: Ball joint, which allows rotation around x, y, and z, Hinge joint, which allows rotation around z Slider joint, which allows translation along x. Robot::Effectors Components to accomplish some desired physical function Examples: Hands Wheels Torch Legs Robot::Actuators Actuators are the muscles of the robot. These can be electric motors, hydraulic systems, pneumatic systems, or any other system that can apply forces to the system. Robot::Sensors Allow for perception. Sensors can be active or passive: Active derive information from environments reaction to robots actions, e.g. bumpers and sonar. Passive observers only, e.g. cameras and microphones .

Emulating Human Attributes: Voice Recognition Humans, when interpreting speech, are able to fill in the blanks, read body language, eliminate background noise and appreciate the context.

Interpretation of continuous speech requires the use of an immense knowledge base and immense comparison operations. Alternatives to von Neumann architecture are needed to provide the required computer processing power.

Emulating Human Attributes: Vision Systems The major problems which exist for vision systems and image recognition are: Interpreting what an image means using pattern recognition technologies. The vision system must recognize what the pattern formed by the image is. Determining the distance of an object (its proximity) in the environment. Emulating Human Attributes: Movement The major difficulty creating robots which can walk has been making them stable and able to move in a variety of directions (motion planning). Various terrains require different types of mobility. Humans have many degrees of freedom with movement. To understand degrees of freedom place your arm straight up in the air and point your index finger at the roof. In how many directions can you move your arm? You can move up and down this is known as pitch. You can move right to left this is known as yaw. You can roll your arm in a circular motion this is known as roll. This gives you 3 degrees of freedom pitch, yaw and roll. Degrees of freedom define the number of independent motions a robot can make.

What is vision? Recognize objects people we know things we own Locate objects in space to pick them up Track objects in motion catching a baseball avoiding collisions with cars on the road Recognize actions walking, running, pushing Vision is really hard Vision is an amazing feat of natural intelligence Vision is multidisciplinary

Robot Ethics: Morality Emotions, sociability, semantic understanding, and consciousness are all important to human moral decision making. It remains an open question whether these will be essential to robots, and if so, whether they can be implemented in machines. Robot Ethics Asimovs Laws of Robotics: Laws 1-3 were published in I, Robot, 1950 Law 0 was added by Asimov later. th 0 ) A robot may not harm humanity, or, by inaction, allow humanity to come to harm. st 1 ) A robot may not injure a human being or, through inaction, allow a human being to come to harm. nd 2 ) A robot must obey orders given it by human beings except where such orders would conflict with the First Law. rd 3 ) A robot must protect its own existence as long as such protection does not conflict with the First or Second Law. Summary Robots as agents act in full complex real world. Tasks, rely on actuators and sensing of environment Exploits perceptions, learning, and reasoning Nothing is totally impossible. Perhaps one day we will be able to produce robots that are practically indistinguishable from ourselves.

What is Computer Vision? Every picture tells a story. Goal of computer vision is to write computer programs that can interpret images. Computer vision is the science and technology of machines that see. Concerned with the theory for building artificial systems that obtain information from images. Computer Vision Computer Vision is the study of analysis of pictures and videos in order to achieve results similar to those as by men. Make computers understand images and videos. What is Computer Vision? A sensor modality for robotics Computer emulation of human vision Inverse of Computer Graphics

Computer Vision vs. Graphics Computer Graphics Produce plausible images. You choose the models, conditions, imaging parameters, etc. Computer Vision Given real images with noise, sampling artifacts Estimate physically quantities What is the minimum world knowledge we need? Other Definitions of CV Trucco and Verri Computing properties of the 3D world from one or more digital images Stockman and Shapiro To make useful decisions about real physical objects and scenes based on sensed images Ballard and Brown The construction of explicit, meaningful description of physical objects from images Forsyth and Ponce Extracting descriptions of the world from pictures or sequences of pictures

*Slide 1-17+ Computer Vision


What is vision? Vision is the process of discovering what is present in the world and where it is by looking.

Problem Areas in Vision The generic "Vision Problem" is far from being solved since no existing system can come close to emulating the capabilities of a human vision. Current systems are fundamentally brittle. As soon as the input deviates ever so slightly from the intended format, the output becomes almost invariably meaningless. Vision is one of the problems of computer science most worthy of investigation because we know that it can be solved, yet we do not know how to solve it well. In fact, to solve the "general vision problem" we will have to come up with answers to deep and fundamental questions about representation and computation at the core of human intelligence. Components of a computer vision system 1. Camera 2. Computer

The following social characteristics are critical to become socially interactive: Communicate with high-level dialogue Learn/recognize models of other agents Establish/maintain social relationships Use natural cues (gaze, gesture, etc.) May learn/develop social competencies Recognize others emotions and/or express their own emotions Exhibit distinctive personality and character

3. Scene

Why do we need to visualize? The purpose of computing is insight, not numbers Richard Hamming Computers produce too much data. Bandwidth of human visual channel is high since large portion of brain devoted to visual processing. An image is worth 1000 words. Images and movies are everywhere. Why do we need to visualize? Fast-growing collection of useful applications building representations of the 3D world from pictures automated surveillance (whos doing what) movie post-processing Searching for a face Gain greater understanding of human vision Challenge: To develop human-level capabilities for computers and robots Various deep and attractive scientific mysteries Current state of the art Earth viewers (3D modeling) Photo Tourism Optical character recognition (OCR) Face / Smile detection Many new digital cameras now detect faces Object recognition (in supermarkets) Face recognition Vision-based biometrics Login without a password Object recognition (in mobile phones) Special effects: shape & motion capture Special effects: image-based rendering Sports / Smart Cars/ Mobileye Vision systems currently in high-end BMW, GM, Volvo models Vision-based interaction (and games) Robotics / Medical Imaging

What is Mood? Determined by perceived signal of punishments and rewards. Modulated by the characters personality. The personality affects the Range of positive moods Range of negative moods Rate of change of moods Mood affects decision-making What is Emotion? Any strong feeling. Feelings such as happiness, sadness, anger, elation, irritation, etc. The feeling one experiences in reaction to a person or situation. A psychological feeling, usually accompanied by a physiological reaction. Emotion has four aspects: Feelings Biological states physiological condition Function motivation, coping, social regulation Expression communication Emotion is not any one of these aspects, but a construct that includes all of them. Emotion occurs as a coordinated, synchronized response process. Three Ways of Measuring Emotion Behavior crying, laughing, facial expression, approach/avoidance, aggression Physiology blood pressure, heart rate, gsr, neural imagining Cognition self-report but also effects on cognitive processes observed indirectly. Emotion affects perception, attention, memory, decision-making, judgments. What is Emotion? Emotions is defined as: Appraisal of a situation as an event: joy, distress; Presumed value of a situation as an effect affecting another: happy-for, gloating, resentment, jealousy, envy, sorry-for; Appraisal of a situation as a prospective event: hope, fear; Appraisal of a situation as confirming or disconfirming an expectation: satisfaction, relief, fears-confirmed, disappointment Manifest temperament control of emotions and this is dependent on ones personality. Plutchik Emotional Model

*Slide 1-18+ Affective Computing (Agents with Emotions)


What is Personality? Personality is defined as the genetic and environmental differences in the brain structures of individuals. It is an essential feature for creating socially interactive agents. It represents those characteristics of the person that account for consistent patterns of feeling, thinking, and behaving. As a species, our brains are almost identical. This gives rise to our common sets of behaviors. But, we are all genetically and environmentally unique. It is the differences that give us our unique behavioral variations of common behavior patterns, i.e., our personality.

Role of Emotion in Intellect Three major areas of Intelligent activity are influenced by emotions Learning Long-term Memory Reasoning An example of highly intelligent, but emotionally challenged characters have been shown here. What is Affect? Affect is the ability to feel. The conscious subjective aspect of feeling or emotion. The observable emotional condition of an individual at any given time. Cognition interprets and makes sense of the world while affect evaluates and judges. Affect promotes better decision making and learning. Typical Human Affect Display occurs through Voice Face Gestures Emotion vs Mood vs Affect Emotion: short term, high intensity, object directed Mood: unfocused, long term, low intensity, Affect: sometimes seen as abstraction of emotion/mood in terms of, positiveness or negativeness and activation or deactivation. Functional Approaches: What does emotion do? It is part of what it means to be human. Emotion makes life worth living by giving value to experiences. Emotion permits us to respond flexibly to our environment, avoiding bad, approaching good. Emotion guides inter-personal relationships. Emotional is necessary to cognitive development because adult-child interaction is facilitated. Emotion and affect influence thought and behavior: The kind of thoughts we have Mood congruency (e.g., positive moods triggers positive thought) The way we process information Broad vs. narrow look A lot vs. a little processing effort What we think about things Emotion/mood as information (howdoes this feel?) Emotion as belief anchor How we learn and adapt Emotion/affect as social reinforcement (emotion expression as signal) Emotion/affect as intrinsic reinforcement (use my own emotion as feedback) Emotion as metaparameter to control learning process (explore vs. exploit) Why do we have emotions? Situational evaluation and communication. Heuristic relating events to personal goals, needs and beliefs: evaluates personal relevance of event and helps decision-making, fast reactions and action preparation influence information processing and decision making e.g, adaptation, attention, search. As a communication medium: communicate internal state (show feelings), alert others (direct attention), show empathy (show understanding of situation). Give feedback (evaluate behavior). Significance of Facial Expressions in Emotions The expression on a faces, is the most basic form of nonverbal communication. Our impression of other people, is highly dependent on their expression.

Classes of Expressions Broadly classified into happy,sad, disgust, fear, anger, surpise and neutral. Goal is to classify an unknown expression into one of these classes What is Affective Computing? Affective computing is computing that relates to, arises from, or deliberately influences emotions. Affective Computing is a field of research in AI dealing with emotions and machines. Address the impact of emotion on intellectual processes, propose a basic theory for recognizing emotions, survey a few existing techniques applied in affective computing, and motivate the reason for controlled integration of these techniques in AI. Different types of computer models: recognize emotions, interpret/elicit emotions, emotional influence on behavior (adaptation, attention), show emotions, and complex mixtures of these models An affective computing system is a system of computational processes that perceives, expresses, interprets, or uses emotions, e.g. a robot, a virtual character, a tutor agent, a fridge, etc Assistive robotics Aibo (Sony, Japan) Entertainment robot I-Cat (Philips, NL) Robot assistant for elderly people Paro (Wada et al, Japan) Robot companion for elderly Huggable (MIT, USA) Robot companion for elderly Why is Affective Computing Useful? Advance emotion theory simulated agents that elicit emotions to study possible psychological structure of emotions. emotion as artificial motivator (e.g. a bored robot that explores). Understand intelligence and adaptation laws and rules are not sufficient for understanding or predicting human behavior and intelligence (e.g. how to sift thru many possible choices) simulated learning agents influenced by emotions (e.g., emotion as reward) Why is Affective Computing Useful? Facilitate Human-Computer (Robot) interaction use emotions in simulated-agent plans (to simulate human reasoning) communication and joint attention robot acceptation Persuasive design (VR training, tutor agents) Interactive robot learning Entertainment Computer games such as the Sims (EA), Aibo Robot (Sony). Summary Affective computing is about computing with emotions. a system of computational processes that perceives, expresses, interprets, or uses emotions Affective Computing is useful because: it can advance emotion theory, we can understand intelligence better, it can facilitate Human-Computer (Robot) interaction, and of its importance in entertainment.

S-ar putea să vă placă și