/sci/ - Science & Math

Unsupervised Predictive Memory in a Goal-Directed Agent
>We develop a model, the Memory, RL, and Inference Network (MERLIN), in which memory formation is guided by a process of predictive modeling. MERLIN facilitates the solution of tasks in 3D virtual reality environments for which partial observability is severe and memories must be maintained over long durations. Our model demonstrates a single learning agent architecture that can solve canonical behavioural tasks in psychology and neurobiology without strong simplifying assumptions about the dimensionality of sensory input or the duration of experiences.
https://arxiv.org/abs/1803.10760

The Kanerva Machine: A Generative Distributed Memory
>We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them.
>Empirically, we demonstrate that the adaptive memory significantly improves generative models trained on both the Omniglot and CIFAR datasets. Compared with the Differentiable Neural Computer (DNC) and its variants, our memory model has greater capacity and is significantly easier to train.
https://arxiv.org/abs/1804.01756

Learning to learn with backpropagation of Hebbian plasticity
>As a result, the networks "learn how to learn" in order to solve the problem at hand: the trained networks automatically perform fast learning of unpredictable environmental features during their lifetime, expanding the range of solvable problems. We test the algorithm on various on-line learning tasks, including pattern completion, one-shot learning, and reversal learning. The algorithm successfully learns how to learn the relevant associations from one-shot instruction, and fine-tunes the temporal dynamics of plasticity to allow for continual learning in response to changing environmental parameters.
https://arxiv.org/abs/1609.02228

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
https://arxiv.org/abs/1712.01815