Higher order associative memories and their optical implementations
نویسندگان
چکیده
The properties of higher order memories are described. The non-redundant, up to Nth order polynomial expansion of N-dimensional binary vectors is shown to yield orthogonal feature vectors. The properties of expansions that contain only a single order are investigated in detail and the use of the sum of outer product algorithm for training higher order memories is analyzed. Optical implementations of quadratic associative memories" are described using volume holograms for the general case and planar holograms for shift invariant memories.
منابع مشابه
A Connectionist Model of False Memories
We present a connectionist model of false memories called the Associative Self-Organizing Network (ASON) model. Four mechanisms underlying the Constructive Memory Framework (CMF) guide the design of the ASON model, a connectionist operationalisation of the CMF. Simulation studies of experiments in the DRM paradigm reveal the ASON model to exhibit false memories. In addition, the effects of Mean...
متن کاملNeural Associative Memories
Despite of processing elements which are thousands of times faster than the neurons in the brain, modern computers still cannot match quite a few processing capabilities of the brain, many of which we even consider trivial (such as recognizing faces or voices, or following a conversation). A common principle for those capabilities lies in the use of correlations between patterns in order to ide...
متن کاملThe Linear Quantization Strategy of Quadratic Hebbian-Type Associative Memories and Their Performance Analysis
The Quadratic Hebbian-type associative memories have superior performance, but they are more difficult to implement because of their large interconnection values in chips than are the first order Hebbian-type associative memories. In order to reduce the interconnection value for a neural network with M patterns stored, the interconnection value [− M, M] is mapped to [− H, H] linearly, where H i...
متن کاملEvolutionary analysis of hierarchically coupled associative memories
Inspired by the theory of neuronal group selection (TNGS), we have carried out an analysis of the capacity of convergence of a multi-level associative memory based on coupled generalized-brain-state-in-a-box (GBSB) networks through evolutionary computation. The TNGS establishes that a memory process can be described as being organized, functionally, in hierarchical levels where higher levels co...
متن کاملBengali character recognition using Bidirectional Associative Memories (BAM) neural network
This paper presents the recognition features of Bengali text using BAM (Bidirectional Associative Memories) neural network with a proposal of feature extraction procedure of a Bengali character. To do this, the conventional methods are used for text scanning to segmentation of a text line to a single character. In this paper an efficient procedure is proposed for boundary extraction, scaling of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural Networks
دوره 1 شماره
صفحات -
تاریخ انتشار 1988