Entropic Associative Memory for Manuscript Symbols
This work addresses memory retrieval challenges in computational models, offering a novel approach for practical applications, though it appears incremental compared to neural network models.
The paper tackles the problem of storing and retrieving manuscript symbols using an entropic associative memory, achieving direct rejection of non-contained cues and handling occlusions through parallel computations.
Manuscript symbols can be stored, recognized and retrieved from an entropic digital memory that is associative and distributed but yet declarative; memory retrieval is a constructive operation, memory cues to objects not contained in the memory are rejected directly without search, and memory operations can be performed through parallel computations. Manuscript symbols, both letters and numerals, are represented in Associative Memory Registers that have an associated entropy. The memory recognition operation obeys an entropy trade-off between precision and recall, and the entropy level impacts on the quality of the objects recovered through the memory retrieval operation. The present proposal is contrasted in several dimensions with neural networks models of associative memory. We discuss the operational characteristics of the entropic associative memory for retrieving objects with both complete and incomplete information, such as severe occlusions. The experiments reported in this paper add evidence on the potential of this framework for developing practical applications and computational models of natural memory.