The structure of evolved representations across different substrates for artificial intelligence
Artificial neural networks (ANNs), while exceptionally useful for classification, are vulnerable to misdirection. Small amounts of noise can significantly affect their ability to correctly complete a task. Instead of generalizing concepts, ANNs seem to focus on surface statistical regularities in a given task. Here we compare how recurrent artificial neural networks, long short-term memory units, and Markov Brains sense and remember their environments. We show that information in Markov Brains is localized and sparsely distributed, while the other neural network substrates "smear" information about the environment across all nodes, which makes them vulnerable to noise.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
The Information-Theoretic Imperative: Compression and the Epistemic Foundations of Intelligence
Why do brains and deep networks converge on similar representations? Task-optimized artificial neural networks quantitatively predict primate ventral stream responses despite radically different substrates and optimizati…
Universal Mechanical Polycomputation in Granular Matter
Unconventional computing devices are increasingly of interest as they can operate in environments hostile to silicon-based electronics, or compute in ways that traditional electronics cannot. Mechanical computers, wherei…
From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage
DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low maintenance cost. Over the past decade, substantial progress has bee…
Machine learning modeling of family wide enzyme-substrate specificity screens
Biocatalysis is a promising approach to sustainably synthesize pharmaceuticals, complex natural products, and commodity chemicals at scale. However, the adoption of biocatalysis is limited by our ability to select enzyme…
BIG-bench Machine LearningDrug DiscoverySpecificityRemapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems
The emerging field of diverse intelligence seeks an integrated view of problem-solving in agents of very different provenance, composition, and substrates. From subcellular chemical networks to swarms of organisms, and a…