What Is Continual Learning?

Ronak Malde tells Pat Grady and Lauren Reeder that the human brain is the model for real continual learning. People are true continual learners because they learn online and keep updating and iterating. Agents and AI today are only pseudo-continual learning.

On family road trips, his family went to AAA, picked up maps, and had the whole route highlighted before they left. Changing the route later meant calling AAA or going to a physical location. Agents now are very intelligent and come with mapping algorithms, but you can consult them only offline in a couple of places. Any course change still takes an entire mass batch update. The first goal at Trajectory is to democratize training models and customizing them for what people want. He compares that stage to MapQuest: the map is still offline, yet anyone can map the algorithms without a trip to AAA. The final stage of continual learning is closer to Google Maps. Every time you are driving, every route updates, and the system learns in aggregate what the fastest route is and where the traffic is.

He wants continual learning to reach that always-updating map.