id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_eytfreollragxo26ezexsnsqqa	Andrés Pomi	Context-sensitive autoassociative memories as expert systems in medical diagnosis	2006	11	.pdf	application/pdf	6586	805	58	Results: We show here that matrix memory models with associations modulated by context can Conclusion: Context-dependent associative memories can operate as medical expert systems. Associative memories are neural network models developed to capture some of the known characteristics of The neural module receives the input of two vectors: one representing the set of possible diseases up to the moment and the other vector corresponding to a new sign, symptom or laboratory result. This output vector is a linear combination of a narrower set of disease vectors that can be reinjected if a new clinical data arrives or can be processed to obtain the probability These 15 vectors representing the clinical presentation of the neonates with the diagnosis of suspected sepsis are shown in Figure 5. The set of signs and symptoms associated with three different diseases column vectors mapping signs and symptoms accompanying the i disease (also an orthonormal set), and � is the	./cache/work_eytfreollragxo26ezexsnsqqa.pdf	./txt/work_eytfreollragxo26ezexsnsqqa.txt