General Neurodynamic Associative Memory Model

点击翻译按钮获取中文摘要

Although it is something most of us do every day without effort, memorizing is in fact an incredibly complex task. For instance, the simple act of storing and retrieving an object is something we have not yet managed to program a machine to do with anything approaching human efficiency and robustness. My research aims to better understand how human cognitive system accomplishes the complex task of create (and enhance) representation from patterns as well as recognize, identify, categorize and classify them. In particular, this research focuses on an interesting nonlinear dynamics system perspective where time and change are the key variables. Within that perspective memory are represented as invariant states of the system. To understand how the human cognitive system works, we need to develop formal models. Nowadays, no formal models can take into account this variety of behavior without scarifying simplicity and self-consistency. In this research, we will use artificial neural networks that are parallel and where information is distributed among the units. Since the brain uses similar computing units and mechanisms for different tasks, this approach uses a general bidirectional associative memory model as building blocks for a general cognitive architecture. This research aims to take into account unsupervised, unsupervised and reinforcement learning using a unique model. The model must have the flexibility to adapt itself in regards to neuroscience and cognition constraints. It is hoped that by developing a general bidirectional associative memory we will have a better understanding on how the mind works and how this understanding can be translated into computational intelligence