Blog

Type

Experiment 24General 30Reading List 16Theory 55

Topics

CLA 13Reinforcement Learning 13HTM 11Hierarchical Generative Models 10Sparse Distributed Representations 10Neocortex 9Deep Learning 8Cortical Learning Algorithm 7Predictive Coding 7columns 6Hippocampus 6Temporal Pooling 6Thalamocortical 6unsupervised learning 6hierarchy 5neurobiology 5pyramidal cell 5

  1. An unexpected success in zero-shot, few-shot and streaming RL

    In the last blog we looked at the phenomenon of “jagged intelligence” — the paradox that AIs are simultaneously superhuman and stupid in adjacent skills. We identified a lack of continual, fast learning and embodiment as possible causes of this weirdness, and noted that embodiment is also a “learning problem”, because current ML models can’t learn from a single thread of…

  2. Not like us: Why AI feels alien, and how to fix it

    Introduction Will highly intelligent machines inevitably think like us? Our experiences with AI that is simultaneously incredibly powerful and incredibly flawed are evidence that not all forms of intelligence are the same. Until recently, all human-level intelligence was human. Now, AI seems to threaten our monopoly. But truly human-level and human-like artificial general intelligence (AGI) is still quite…

  3. HRM-Agent: Using the Hierarchical Reasoning Model in Reinforcement Learning

    Authors: Hoang Long Dang and David RawlinsonUPDATE: Full HRM-Agent paper now available. When the Hierarchical Reasoning Model was released, we were very excited about its combination of small size and impressive reasoning abilities. These qualities seem to be enhanced by recurrent processing, but with a surprisingly simple gradient update based on the converged recurrent forward state — turning a…

  4. Why I’m excited about the Hierarchical Reasoning Model

    Since the arrival of Chat GPT, I’ve felt that progress in AI has been largely incremental. Of course, even Chat GPT was/is mostly just a scaled up Transformer model, which was introduced by Vaswani et al in 2017. The belief that AI is advancing relatively slowly is a radical and unpopular opinion these days, and it’s been…

  5. Grant – Continual Few-Shot Learning

    We are very happy to announce that we’ve been awarded an Artificial Intelligence for Decision Making Initiative grant from Defence Science Institute on Effective updating of deep learning models with limited new data. More specifically, the grant is for the Continual Few-Shot Learning project that we blogged about recently.

  6. Continual Few-Shot Learning with Hippocampal Replay

    In continual learning, the neural network learns from a stream of data, acquiring new knowledge incrementally. It’s not possible to assume an i.i.d. stationary dataset available in one batch. Catastrophic forgetting of previous knowledge is a well known challenge. A wide variety of approaches fall broadly into 3 categories [6]: Regularization-based methods, Parameter isolation methods…

  7. Video Prediction using Recurrent Sparse Memory

    We recently presented 2 papers at the International Joint Conference on Neural Networks, IJCNN. The first one is about one-shot learning for the long term (with an artificial hippocampal algorithm), blog here. In this blog article, we are excited to share the other paper – Learning distant cause and effect using only local and immediate credit assignment…

  9. Towards Biologically Inspired Executive Control

    Executive Control is core to what most people recognise as true intelligence. For example, the ability to attend to relevant cues and maintain task dependent information whilst ignoring distracting details and taking appropriate actions. Working Memory (WM) is a core component of Executive Control. “Working memory is a short-term repository for task-relevant information that is…