Random boolean networks also have some surprising properties.
Computerphile demonstrates how complex systems can arise from simple rules.
Dr Alex Turner generates some
Computerphile explores genetic algorithms and all the processes it encompasses: tournament selection, roulette selection, mutation, crossover, etc.
Computerphile explains why laziness may be a virtue (in programming).
Professor Thorsten Altenkirch on how you can use the ‘yield’ to compute certain things “on demand”
Computerphile presents Memristors, Artificial Synapses & Neomorphic Computing. Dr Phil Moriarty on the limitations of the Von Neumann architecture and what could be next.
Related Links:
- Phil’s blog post: https://muircheartblog.wpcomstaging.com/2020/09/10/i-remember-now
- Von Neumann Architecture: https://www.youtube.com/watch?v=Ml3-kVYLNr8
Half Ideas – Startups and Entrepreneurship takes a closer look at GPT-3 and what it means for AI.
GPT 3 can write poetry, translate text, chat convincingly, and answer abstract questions. It’s being used to code, design and much more. I’ll give you a demo of some of the latest in this technology and some of how it works.
GPT 3 has been developed for a number of years. One of the early papers published was on Generative Pre-Training. The idea behind generative pre-training (GPT) is that while most AI’s are trained on labeled data, there’s a ton of data that isn’t labeled. If you can evaluate the words and use them to train and tune the AI it can start to create predictions of future text on the unlabeled data. You repeat the process until predictions start to converge.
Speaking of infrastructure, did you ever wonder how do websites marry up to their IP addresses?
Dr Mike Pound explains the Domain Name System – DNS in this Computerphile video.
Computerphile takes look at the technology that may help health services to work out how viruses can spread.
For Mathematics, trees are more useful than strings.
Professor Thorsten Altenkirch takes us through a functional approach to coding them in Python.
Professor Thorsten Altenkirch demonstrates a recursive Sudoku solver.
Rob Miles of Computerphile discusses the idea of a gym for training AI algorithms.