paper-with-me

홈 › Papers

Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes

2008-12-23 · Juergen Schmidhuber

I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more beautiful. Curiosity is the desire to create or discover more non-random, non-arbitrary, regular data that is novel and surprising not in the traditional sense of Boltzmann and Shannon but in the sense that it allows for compression progress because its regularity was not yet known. This drive maximizes interestingness, the first derivative of subjective beauty or compressibility, that is, the steepness of the learning curve. It motivates exploring infants, pure mathematicians, composers, artists, dancers, comedians, yourself, and (since 1990) artificial systems.

📄 PDF Abstract BibTeX arXiv:0812.4360

Code (1)

geohot/twitchcoq

Similar Papers 제목 키워드 기반

HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression

2025-08-04 · Junhao Cai, Taegun An, Chengjun Jin, Sung Il Choi 외 arxiv

Distributed multi-stage image compression -- where visual content traverses multiple processing nodes under varying quality requirements -- poses challenges. Progressive methods enable bitstream truncation but underutili…

Computational EfficiencyImage Compression

A Compression Perspective on Simplicity Bias

2026-03-26 · Tom Marty, Eric Elmoznino, Leo Gagnon, Tejas Kasetty 외 arxiv

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Lengt…

MedCore: Boundary-Preserving Medical Core Pruning for MedSAM

2026-05-13 · Cenwei Zhang, Suncheng Xiang, Lei You arxiv

Medical segmentation foundation models such as SAM and MedSAM provide strong prompt-driven segmentation, but their image encoders are still too large for many clinical settings. Compression is also risky in medicine beca…

Polyp Segmentation

Fundamental principles of cortical computation: unsupervised learning with prediction, compression and feedback

2016-08-19 · Micah Richert, Dimitry Fisher, Filip Piekniewski, Eugene M. Izhikevich 외

There has been great progress in understanding of anatomical and functional microcircuitry of the primate cortex. However, the fundamental principles of cortical computation - the principles that allow the visual cortex …

Visual Tracking

Estimating Information Flow in DNNs

2019-05-01 · ICLR 2019 5 · Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Brian Kingsbury 외

We study the evolution of internal representations during deep neural network (DNN) training, aiming to demystify the compression aspect of the information bottleneck theory. The theory suggests that DNN training compris…

Clustering