Advanced Artificial Intelligence

An advanced artificial intelligence course by Dr. Michael S. Gashler.

This course investigates some advanced topics in artificial intelligence, including deep Q-learning, kd-trees, nonlinear dimensionality reduction, cognitive architectures, using the extended Kalman filter with neural networks, and Bayesian graphical models (a.k.a. belief networks). (Watching the videos without completing all of the projects does not count as taking this course.)

Lecture 1 cartpole game	Lecture 2 discounting future rewards	Lecture 3 explore vs exploit
Lecture 4 code walk-through	Lecture 5 where your code goes	Lecture 6 adding the neural net
Lecture 7 k-order MDPs	Lecture 8 Bellman equation	Lecture 9 implementation details
Lecture 10 ultimate doughnut	Lecture 11 car on hill	Lecture 12 epsilon greedy
Programming Assignment 1 Deep Q-learning with cart-pole
Lecture 13 A1 post mortem	Lecture 14 Atari games	Lecture 15 utility shape
Lecture 16 chain rule	Lecture 17 chaining models	Lecture 18 actor-critic model
Lecture 19 read paper	Lecture 20 equations	Lecture 21 more equations
Lecture 22 actor- critic	Lecture 23 A3C	Lecture 24 More A3C
Lecture 25 diagramming AI	Lecture 26 more diagramming	Lecture 27 intro to k-NN
Lecture 28 feature scaling	Lecture 29 visualizing k-NN
Lecture 30 ball vs. kd trees	Lecture 31 kd-tree intuition	Lecture 32 implementing kd-trees
Lecture 33 distance to kd node	Lecture 34 comparing learners	Lecture 35 more comparing
Lecture 36 correlation	Lecture 37 distance metrics	Lecture 38 L^p-Norm
Programming Assignment 2 Instance-based learning
Lecture 39 PCA	Lecture 40 more PCA	Lecture 41 spherical distribution
Lecture 42 medoids	Lecture 43 PCA with cat data	Lecture 44 Gram-Schmidt
Lecture 45 accuracy of k-NN	Lecture 46 Multi-dimensional scaling	Lecture 47 More MDS
Lecture 48 nonlinear axes	Lecture 49 Swiss roll	Lecture 50 knee of curve
Lecture 51 manifold of faces	Lecture 52 transduction	Lecture 53 intrinsic variables
Lecture 54 summarize MDS	Lecture 55 summarize Isomap	Lecture 56 summarize MVU
Programming Assignment 3 Dimensionality reduction
Lecture 57 traveling salesman	Lecture 58 relaxation
Lecture 59 auto-associative memory	Lecture 60 RBMs and regularization	Lecture 61 intro to paper
Lecture 62 Q&A about dimred	Lecture 63 more Q&A	Lecture 64 equations inpaper
Lecture 65 review for midterm
Midterm Exam
Lecture 66 answers 1-5	Lecture 67 answers 6-end
Midterm Answer Key
Lecture 68 about papers	Lecture 69 more on GANs
Lecture 70 pixels to torques	Lecture 71 finish P2T	Lecture 72 Kalman project
Lecture 73 merging beliefs	Lecture 74 extended Kalman filter
Lecture 75 Kalman equations	Lecture 76 more Kalman	Lecture 77 extended Kalman equations
Lecture 78 finite differencing	Lecture 79 backprop	Lecture 80 Assignment details
Lecture 81 more Kalman	Lecture 82 more Kalman	Lecture 83 more Kalman
Lecture 84 more Kalman	Lecture 85 more Kalman	Lecture 86 more Kalman
Programming Assignment 4 Extended Kalman Filter
Lecture 87 derive Bayes' law	Lecture 88 graphical models	Lecture 89 graphical model project
Lecture 90 Markov chains	Lecture 91 how GM is MC
Lecture 92 Kalman clarifications	Lecture 93 GM details
Lecture 94 Gibbs sampling	Lecture 95 Metropolis- Hastings
Lecture 96 skewed data	Lecture 97 GM and NN	Lecture 98 More GM
Lecture 99 debugging GM	Lecture 100 more debugging
Programming Assignment 5 Bayesian Graphical Models
Lecture 101 Bayes optimal classifier	Lecture 102 uncertainty	Lecture 103 optimal ensembles