Recognition capabilities of a Hopfield model with auxiliary hidden neurons

We study the recognition capabilities of Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. show that such at zero temperature outperform those original model, due to substantial increase storage capacity and lack defined basin attraction. The modified does not fall abruptly into regime complete confusion when memory load exceeds sharp threshold. This latter circumstance, together an capacity, renders promising candidate for further research, possible diverse applications.