[email protected]: Fall 2017
This Semester's PlanOur first offering of Core. We started out with a history of neural networks and learned to implement them, from sratch. We then delved into Reinforcement Learning and further explored Evolutionary Computation.
Be sure to check individual meeting times – as we occasionally have to stray from the schedule!
: Introductions & an Intro to Neural Networks
Welcome back to SIGAI! 😃 Tonight we'll go over some changes that have happened over the summer, how we'll handle things after moving forward, then dive into our classic first lecture/workshop series, An Intro to Neural Nets. This time, though, we'll go into significantly more depth, historically and mathematically, than we have in the past. See you there!
: an Intro to Neural Nets
UPDATE: We've partnered with TechKnights to throw a lecture+workshop combo during KnightHacks! To finish Unit 0 for the Fall series, we're following up our lecture last week with a workshop. Here, we'll build a neural network to classify hand-written digits using a popular dataset, MNIST, with some help from Google's Tensorflow library. ***Everything will be provided in a self-contained environment for you but you will need to come prepared with the below requirements before the workshop begins.
: Introduction to Reinforcement Learning
We're starting Unit 1 on Reinforcement Learning! This is the lecture for that series. Here, we'll cover the problem of learning through interaction, what RL is, how it's different from Supervised Learning, how RL is formalized (math), and what Markov Decision Processes are Dynamic Programming is. There is no background knowledge needed for this lecture other than simple arithmetic, college algebra, and basic probability theory. We'll be doing a short refresher on the necessary concepts if need be 🙂. Hope to see you there!
: Intro to Reinforcement Learning, Part 2
Hey! This will be our second lecture in Unit 1 on Reinforcement Learning! We'll be reviewing what we learned about Markov Decision Processes and then go over Dynamic Programming, a method of solving Markov Decision Problems and the theoretical foundation for most solutions to modern RL problems. Come on out!
: Intro to Evolutionary Computation
Hey SIGAI, We're beginning our Unit 2 on Advanced Topics with a lecture on evolutionary computation by Dr. Annie Wu from UCF's Computer Science Department! She'll be giving the introductory lecture she gives to her graduate students in her Evolutioanry Computation course here at UCF. There will be no slides for this lecture so if you're curious to know, come out! It is going to be a great primer for our following lecture on neuroevolution. More about Dr. Wu: Dr. Wu is the Director of the Evolutionary Computation Lab at UCF and an Associate Professor in the Department of Computer Science. Find more here: http://www.cs.ucf.edu/~aswu/
: Introduction to Neuroevolution
Welcome to our second to last lecture for Fall 2017! We will be giving an introduction to neuroevolution, one of the most active subfields in evolutionary computation! We will be covering history, prominent algorithms and frameworks, current state-of-the-art research going on in the field here at UCF, and the recent attention this field has gotten from big names such as Google Brain, DeepMind, FAIR, Uber, MIT, and more!
Officers, Guests, and Advisors
Guest Speaker: Core
[email protected]: Spring 2018
We’ve made some modifications to the content and polished the lecture-workshops, while still sticking true to our deep-learning and reinforcement-learning focus. We added both Convolutional and Recurrent Neural Networks to our content, with a focus on a deeper technical understanding.