18532826. METHOD FOR MAPPING AN INPUT VECTOR TO AN OUTPUT VECTOR BY MEANS OF A MATRIX CIRCUIT simplified abstract (Robert Bosch GmbH)
Contents
METHOD FOR MAPPING AN INPUT VECTOR TO AN OUTPUT VECTOR BY MEANS OF A MATRIX CIRCUIT
Organization Name
Inventor(s)
Tobias Kirchner of Stuttgart (DE)
Taha Soliman of Stuttgart (DE)
Thomas Kaempfe of München (DE)
METHOD FOR MAPPING AN INPUT VECTOR TO AN OUTPUT VECTOR BY MEANS OF A MATRIX CIRCUIT - A simplified explanation of the abstract
This abstract first appeared for US patent application 18532826 titled 'METHOD FOR MAPPING AN INPUT VECTOR TO AN OUTPUT VECTOR BY MEANS OF A MATRIX CIRCUIT
The disclosure pertains to a method for mapping an input vector to an output vector using a matrix circuit with memory cells arranged in rows and columns, each cell having an adjustable memory state and generating an electrical current based on applied voltages.
- Memory cells in the matrix circuit have semiconductor switching elements with control terminals connected to specific lines.
- Input voltages corresponding to components of the input vector are applied to the first lines.
- A ramp voltage is applied to the second line of each column, increasing with time.
- Total current at the third line of a column is detected until it reaches a certain threshold, determining an elapsed time period.
- The output vector component for a column is determined based on the elapsed time period.
Potential Applications: - Signal processing - Neural networks - Pattern recognition systems
Problems Solved: - Efficient mapping of input vectors to output vectors - Improved memory cell functionality
Benefits: - Enhanced data processing capabilities - Increased accuracy in output vector generation
Commercial Applications: Title: "Advanced Matrix Circuit for Data Mapping" This technology can be utilized in: - Machine learning systems - Image recognition software - Data analysis tools
Questions about the technology: 1. How does the adjustable memory state in the memory cells impact the mapping process? 2. What advantages does the ramp voltage method offer compared to traditional mapping techniques?
Original Abstract Submitted
The disclosure relates to a method for mapping an input vector to an output vector by means of a matrix circuit which has memory cells arranged in a matrix in a plurality of rows and a plurality of columns and first, second and third lines, each memory cell having an adjustable memory state, is connected to the first line () of the corresponding row, is connected to the second and third lines of the corresponding column and is set up to generate an electrical current (I, I, I) depending on the memory state and voltages applied to the first, second and third lines, is connected to the second and third lines of the corresponding column and is arranged to conduct an electric current (I, I, I) into the third line () as a function of the memory state and voltages applied to the first, second and third lines, each memory cell having a semiconductor switching element () with a control terminal which is connected to the second line () of the corresponding column; wherein input voltages (U, U, U) corresponding to components of the input vector are applied () to the first lines; wherein for each column: a ramp voltage (V, V, V) is applied () to the second line assigned to the column, the level of which is increased with time (); a total current is detected at the third line assigned to the column and a time period elapsed since a start time of the level increase of the corresponding ramp voltage is determined () until the magnitude of the total current reaches a certain current magnitude threshold (Ig) (); and a component of the output vector corresponding to the column is determined () based on the elapsed time period (t, t, t).
