Executive Control is core to what most people recognise as...
Read MoreCerenaut Research
General-purpose machine learning
FEATURED RESEARCH
Algorithms for learning using only local and immediate credit assignment
High-order partially-observable sequences
Recurrent Sparse Memory (RSM) is an unsupervised method for simultaneously learning spatial and sequential structure in partially-observable high Markov order data streams
Fast (One-shot) episodic learning
Our Artificial Hippocampus Algorithm (AHA) can learn to generalize classes from a single instance, while still discriminating between instances of the same class - all without any provided labels
Research Strategy
We aim to discover new learning rules, architectures and representations by using computational neuroscience discoveries to guide our research
NEWS
- Nov 2020: Satya presents paper at AI2020, on self-organising networks
- Nov 2020: Gideon presents paper at AI2020, on one-shot learning of instances as well as classes, using AHA (hippocampal architecture)
- Nov 2020: Satya presents poster at NAISys on self-organising networks
- Nov 2020: Gideon presents poster at NAISys on using AHA to consolidate memories
- Sep 2020: Jeremy (Numenta) presents the paper from our collaboration, at ANNPR, on Boosted RSM
RECENT ARTICLES
Max Bennett on a canonical Neocortical Microcircuit [Numenta meeting]
Check out this fascinating research meeting with Numenta and guest...
Read More
5th WBAI Hackathon
The Whole Brain Architecture Initiative (WBAI) aims to foster research...
Read MoreAbout Us
Cerenaut (formerly ProjectAGI) undertakes fundamental research in artificial intelligence & machine learning. We’re based in Melbourne, Australia.
We collaborate with academic institutions, companies and individuals, on topics of shared interest. If you’d like to work with us, get in touch! We co-supervise student research projects and engage with the research community here in Australia.