The second HumemAI research paper A Machine with Short-Term, Episodic, and Semantic Memory Systems, showed that a reinforcement learning (RL) agent can learn a memory management policy. We wanted more. We wanted to see if it can learn other cognitive functions too, such as maze navigation. That’s what we addressed...
[Read More]
The first HumemAI research paper A machine with human-like memory systems, didn’t use any machine learning. Machine learning reinforcement learning (RL). All the memory management policies used there were handcrafted. They might be fine, as long as they work fine. But handcrafted functions are rigid and won’t be able to...
[Read More]
This paper was my first attempt to create a conscious AI. I got pretty interested in human memory after reading the works of Endel Tulving. He argued that what makes us human conscious is that we have episodic memory, which is one of the two pillars of explicit memory (the...
[Read More]