Reinforcement learning in AI

Reinforcement learning Reinforcement learning is like many topics with names ending in -ing, such as machine learning, planning, and mountaineering, in that it is simultaneously a problem, a class of solution methods that work well on the class of problems, and the field that studies these problems and their solution methods. Reinforcement learning problems involve … Read more

Utility theory in Artificial intelligence

There are following points about Utility theory Defines axioms on preferences that involve uncertainty and ways to manipulate them. Uncertainty is modeled through lotteries -– Lottery: [ p : A;(1 − p) : C] Outcome A with probability p Outcome C with probability (1-p) The following six constraints are known as the axioms of utility … Read more

Probabilistic reasoning in Artificial intelligence

Need of Probabilistic Reasoning in AI Unpredictable outcomes Predicates are too large to handle Unknown error occurs In probabilistic reasoning, there are two methods to solve difficulties with uncertain knowledge Bayes’ rule Bayesian Statistics Probability: Probability can be defined as chance of occurrence of an uncertain event. It is the numerical measure of the likelihood … Read more

Forward and Backward Chaining in Artificial intelligence

Forward chaining starts with the available data. This is an initial data and uses inference rules. It helps in extracting more data until a goal is reached. An inference engine using forward chaining searches the inference rules until it finds one. Here the antecedent is known to be true. Whenever such a rule is found, … Read more

Inference in First order logic in Artificial intelligence

There are two ideas behind Inference in First order logic in Artificial intelligence convert the KB to propositional logic and use propositional inference a shortcut that manipulates on first-order sentences directly (resolution, will not be introduced here) Universal Instantiation infer any sentence by substituting a ground term (a term without variables) for the variable Examples … Read more

Uniform cost search in AI

uniform-cost search expands the node n with the lowest path cost g(n). This is done by storing the frontier as a priority queue ordered by g Uniform-cost search on a graph function UNIFORM-COST-SEARCH(problem) returns a solution, or failure node ←a node with STATE = problem.INITIAL-STATE, PATH-COST = 0 frontier ← a priority queue ordered by … Read more

Measuring problem-solving performance in AI

We can evaluate an algorithm’s performance in four ways in Artificial intelligence Completeness Optimality Time complexity Space complexity Time and space complexity are always considered with respect to some measure of the problem difficulty. In theoretical computer science, the typical measure is the size of the state space graph, |V | + |E|, where V … Read more

Building AI Systems

Perception Intelligent biological systems are physically embodied in the world and experience the world through their sensors (senses). For an autonomous vehicle, input might be images from a camera and range information from a rangefinder. For a medical diagnosis system, perception is the set of symptoms and test results that have been obtained and input … Read more