Paper Reading AI Learner

Knowledge as Fruits of Ignorance: A global Free Energy Principle of our way of thinking

2022-06-12 07:28:05
Cailleteau Thomas

Abstract

In this second article, we show a simple use of the Ignorance as defined in "Jaynes & Shannon's Constrained Ignorance and Surprise". By giving an example about the journey of a person, we believe to show some simple, obvious but mathematically encoded philosophical implications about how we could think, learn and memorize. In this basic model we will separate how we learn from Ignorance, and how we anticipate the world using Bayes formula, both should however be more entangled to best reflect reality. In fact, as we have seen after achieving this work, applying Ignorance on the system constituting a person finally turns out to be the global approach of its local counterpart on systems like neurons, cells and other complex probabilistic systems, described using the free energy principle, a much more complex and detailed approach. The aim of this article is therefore to show, as seen from a person, another aspect of the application of the free energy principle which represents the constrained Shannon's entropy, and leads to Bayes'formula. We show that, using only ignorance as a single quantity, and its minimization as the main process, we can take into account his understandings, assertions, doubts and assumptions about how he perceives the world, by describing them mathematically.

Abstract (translated)

URL

https://arxiv.org/abs/2206.05684

PDF

https://arxiv.org/pdf/2206.05684.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