Timezone: »

 
Poster
Associative Memories via Predictive Coding
Tommaso Salvatori · Yuhang Song · Yujian Hong · Lei Sha · Simon Frieder · Zhenghua Xu · Rafal Bogacz · Thomas Lukasiewicz

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »

Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative memories have been developed for several decades now. In this paper, we present a novel neural model for realizing associative memories, which is based on a hierarchical generative network that receives external stimuli via sensory neurons. It is trained using predictive coding, an error-based learning algorithm inspired by information processing in the cortex. To test the model's capabilities, we perform multiple retrieval experiments from both corrupted and incomplete data points. In an extensive comparison, we show that this new model outperforms in retrieval accuracy and robustness popular associative memory models, such as autoencoders trained via backpropagation, and modern Hopfield networks. In particular, in completing partial data points, our model achieves remarkable results on natural image datasets, such as ImageNet, with a surprisingly high accuracy, even when only a tiny fraction of pixels of the original images is presented. Our model provides a plausible framework to study learning and retrieval of memories in the brain, as it closely mimics the behavior of the hippocampus as a memory index and generative model.

Keywords: Deep Learning · Robustness · Generative Model

Author Information

Tommaso Salvatori (University of Oxford)
Yuhang Song (University of Oxford)
Yujian Hong (University of Oxford)
Lei Sha (Department of Computer Science, University of Oxford)
Simon Frieder (Department of Computer Science, University of Oxford)
Zhenghua Xu (Hebei University of Technology)
Rafal Bogacz (University of Oxford)
Thomas Lukasiewicz (University of Oxford)

More from the Same Authors