Advance AI notes for Android – Latest Version & Features

By the end of the semester the students will be able to:understand the search and decision making techniques used in modern artificial intelligenceapply artificial intelligence techniques in their own codeunderstand the societal and ethical implications of artificial intelligenceHistory and positioning of AI Motivating AI.
Dangers of AI and AGI.
Early history Expert systemsUninformed search Reflex agents Search problems Depth first and breadth first search Uniform cost searchInformed search: A* search and heuristics Informed search methods Heuristics Greedy search A* search Graph searchGame playing and adversarial search Types of games Adversarial search, minimax The problem of depth Evaluation functions Alpha Beta pruningExpect Imax search and utilities Expect Imax search Refresher about probabilities Utilities and rationalityMarkov decision processes 1 Defining MDPs: policies and utilities Optimal policy, value of state, value of Q-stateMarkov decision processes 2 Policy iterationReinforcement learning 1 Reinforcement learning as a twist on MDPsReinforcement learning 2 Exploration vs.
exploitation, regret Generalization across states Policy searchProbability Random variables Joint and marginal distributions, conditional distributionMarkov models Markov chains Conditional independence Stationary distributionsHidden Markov models Hidden Markov models Example: robot localizationParticle filters and applications of HMMs Particle filters Robot localization with particle filters Dynamic Bayes netsClassification, principles of machine learning, naïve Bayes Classification Model-based classification Naive Bayes Spam filter example Generalization and overfitting Parameter estimationIntroduction to deep learning History and impactMachine learning background of deep learning History and impact Machine learning background Loss functions: squared, cross-entropy, soft max Optimization, stochastic gradient descent BackpropagationFeedforward neural networks Feedforward networks Stochastic gradient descentConvolutional neural networks Convolutions Convolutional filters in neural networks Pooling layers