mARC: Memory by Association and Reinforcement of Contexts
This paper introduces the memory by Association and Reinforcement of Contexts (mARC). mARC is a novel data modeling technology rooted in the second quantization formulation of quantum mechanics. It is an all-purpose incremental and unsupervised data storage and retrieval system which can be applied to all types of signal or data, structured or unstructured, textual or not. mARC can be applied to a wide range of information clas-sification and retrieval problems like e-Discovery or contextual navigation. It can also for-mulated in the artificial life framework a.k.a Conway "Game Of Life" Theory. In contrast to Conway approach, the objects evolve in a massively multidimensional space. In order to start evaluating the potential of mARC we have built a mARC-based Internet search en-gine demonstrator with contextual functionality. We compare the behavior of the mARC demonstrator with Google search both in terms of performance and relevance. In the study we find that the mARC search engine demonstrator outperforms Google search by an order of magnitude in response time while providing more relevant results for some classes of queries.
Code (0)
등록된 구현이 없습니다.
Tasks
Artificial LifeQuantizationRetrievalSimilar Papers 제목 키워드 기반
O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generate…
Learning Associative Inference Using Fast Weight Memory
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we a…
Language ModellingMeta Reinforcement LearningQuestion Answeringreinforcement-learning+1MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization
Neural Combinatorial Optimization (NCO) is an emerging domain where deep learning techniques are employed to address combinatorial optimization problems as a standalone solver. Despite their potential, existing NCO metho…
Combinatorial OptimizationDo LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be easily manipulated by changing contexts, ev…
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to hig…
Reinforcement LearningAutonomous Driving