Neural net having a neural processor with distributed synaptic cells

• US 5,649,069 A
• Filed: 06/07/1995
• Issued: 07/15/1997
• Est. Priority Date: 02/26/1992
• Status: Expired due to Fees

• Current Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Original Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Inventors: Gobert, Jean
• Primary Examiner(s): Davis, George B.
• Application Number:
  US08/487,616
• Time in Patent Office: 769 Days
• Field of Search: 395/27, 395/24, 395/22
• US Class Current: 706/41
• CPC Class Codes: G06N 3/063 using electronic means
• CPC Class Codes: G11C 11/419 Read-write [R-W] circuits

Abstract

The neural net has a physical topology independent of its functional topology. Cells, being functional equivalents of synapses, are concatenated to form a unidirectional data path. The cells are connected in parallel to a bus for individual or parallel control The respective synapses contributions to a neuron potential are individually calculated in each respective cell involved. Each cell in the concatenation either is rendered transparent or adds its contribution to the data received from the preceding cell and supplies this sum to the next cell. Preferably, the allocation of the synapses to the cells is programmable.

Claims

1. A neural net comprising:

a neural processor functioning as neurons interconnected by respective synapses, each synapse forming a part of a particular neuron to evaluate an effect of a respective source neuron on the particular neuron, the particular neuron communicating with a respective destination neuron, said neural processor comprising;

(a) at least one concatenation of respective uniform programmable synaptic cells, the concatenation having an entry and an exit, the concatenation forming a data path between the entry and the exit, the respective uniform programmable synaptic cells each acting as a single one of the respective synapses, the uniform programmable synaptic cells in the concatenation being programmable to form at least one group of cells, said one group of cells forming a single neuron, a number of cells in the at least one group also being programmable, each synapse being operative for selectively modifying data in the data path, each uniform programmable synaptic cell having;

(1) a respective data input and a respective data output, the data input of each next one of the cells being connected to the data output of a preceding one of the cells, whereby data is transferred between cells along the concatenation;

(2) a respective calculation unit for performing a respective calculation on data received by the data input and producing selectively modified data at the data output; and

(3) a respective memory, coupled to the respective calculation unit, for storing data received by the data input or produced as modified data by the calculation unit;

(b) bus means for communicating addressed programming instructions to the cells, the cells being connected in parallel to the bus means; and

(c) control means for supplying the addressed programming instructions to control the cells via the bus means in order to select at least one particular one of the cells for at least one of the following operations;

(1) loading a data item received at the respective data entry to the respective memory;

(2) controlling the respective calculation unit to create a respective product by multiplying the data item by a respective synaptic coefficient and storing the product in the respective memory; and

(3) accumulating products which are produced in a plurality of selected cells by transferring a preceding partial sum of products of preceding selected cells to a next one of the selected cells, adding the product stored in the respective memory of the next one of the selected cells to the preceding partial sum to create a next partial sum and providing the next partial sum to the data output of the next selected cell, any non-selected cell being rendered transparent.