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… Read More »An unexpected success in zero-shot, few-shot and streaming RL
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… Read More »Not like us: Why AI feels alien, and how to fix it
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.
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]:… Read More »Continual Few-Shot Learning with Hippocampal Replay