Paper Reading AI Learner

A Neural Network Assembly Memory Model Based on an Optimal Binary Signal Detection Theory

2003-09-21 17:11:11
Petro M. Gopych
arXiv_CV
       
Abstract

A ternary/binary data coding algorithm and conditions under which Hopfield networks implement optimal convolutional or Hamming decoding algorithms has been described. Using the coding/decoding approach (an optimal Binary Signal Detection Theory, BSDT) introduced a Neural Network Assembly Memory Model (NNAMM) is built. The model provides optimal (the best) basic memory performance and demands the use of a new memory unit architecture with two-layer Hopfield network, N-channel time gate, auxiliary reference memory, and two nested feedback loops. NNAMM explicitly describes the dependence on time of a memory trace retrieval, gives a possibility of metamemory simulation, generalized knowledge representation, and distinct description of conscious and unconscious mental processes. A model of smallest inseparable part or an "atom" of consciousness is also defined. The NNAMM's neurobiological backgrounds and its applications to solving some interdisciplinary problems are shortly discussed. BSDT could implement the "best neural code" used in nervous tissues of animals and humans.

Abstract (translated)

URL

https://arxiv.org/abs/cs/0309036

PDF

https://arxiv.org/pdf/cs/0309036.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot