Abstract
Recent achievements on CNN (convolutional neural networks) and DNN (deep neural networks) researches provide a lot of practical applications on computer vision area. However, these approaches require construction of huge size of training data for learning process. This paper tries to find a way for continual learning which does not require prior high-cost training data construction by imitating a biological memory model. We employ SDR (sparse distributed representation) for information processing and semantic memory model, which is known as a representation model of firing patterns on neurons in neocortex area. This paper proposes a novel memory model to reflect remembrance of morphological semantics of visual input stimuli. The proposed memory model considers both memory process and recall process separately. First, memory process converts input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST (Modified National Institute of Standards and Technology) and Fashion-MNIST data sets show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli.
Highlights
Recent deep neural networks and learning algorithms show outstanding performance improvements
This paper proposes a novel memory model to reflect remembrance of morphological semantics of visual input stimuli by combining the concepts of traditional cognitive and psychological memory models [11,12] and a neuron activation simulation model, that is, HTM [13]
This paper proposes a novel scheme for modeling memory mechanism in neocortical region of human brain
Summary
Recent deep neural networks and learning algorithms show outstanding performance improvements. HTM employs modeling memory mechanism in neocortical region of biological brain system. According to HTM model, SDR can be considered as the most representative data format processed by neocortical region of brain. This paper proposes a memory and recall model for morphological semantics within visual stimuli using SDR of HTM model. Neocortical region in biological brain takes in charge of high level of information processing including abstraction and conceptualization for stimuli from the external environment. It supports memory and recall functions when required. In these whole processes, we can model operational mechanism of neurons on neocortical region using SDR operation.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call