EP4158464A1 - Vorrichtung und verfahren zur hardware-basierten zufallszahlen- und zahlenfolgen-generierung - Google Patents
Vorrichtung und verfahren zur hardware-basierten zufallszahlen- und zahlenfolgen-generierungInfo
- Publication number
- EP4158464A1 EP4158464A1 EP21729485.9A EP21729485A EP4158464A1 EP 4158464 A1 EP4158464 A1 EP 4158464A1 EP 21729485 A EP21729485 A EP 21729485A EP 4158464 A1 EP4158464 A1 EP 4158464A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- voltage
- output
- value
- random
- range
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
- G06F7/58—Random or pseudo-random number generators
- G06F7/588—Random number generators, i.e. based on natural stochastic processes
Definitions
- the application relates to a device and a method for hardware-based, genuine random number and number sequence generation, and, in particular, to a device for hardware-based random number generators (RNG) and their operation, in particular, to a device for hardware-based random number generators (RNG ) with electroforming-free memristors.
- the application also relates, in particular, to the structure of the electronic circuit and a method for operating the RNG as a real / true random number generator and as a true random number generator (TRNG; real random number generator) and as a number sequence generator (SNG).
- loT Internet of Things
- Stochastic Computing stochastic computing
- SNG stochastic number generator
- TRNGs are based on the intrinsic stochasticity in physical variables of the system. It has been shown that TRNGs based on silicon CMOS technology can be implemented electronically. A large number of TRNGs are suitable for production on an ASIC silicon process or for implementation on reconfigurable logic platforms, e.g. FPGA (Field Programmable Gate Array; in the field programmable gate arrangement) or CPLD (Complex Programmable Logic Device; complex programmable logic module) .
- the entropy sources of such constructions are, for example, thermal noise due to oscillator jitter [2], Resistance amplifier analog / digital converter chains (see [3]) or metastable elements with capacitive feedback (see [4]).
- the first memristive TRNG was proposed in 2010, see [5],
- RTN random telegraph noise
- TRNG telegraph noise
- RTN from the LRS of a W / TiN / TiON / SiO2 / Si memristors [6]
- RTN is activated or deactivated randomly without predictability
- Balatti et al. proposed a TRNG based on the cycle-to-cycle and component-to-component voltage fluctuations of Cu / AlOx or Ti / HfOx-based memristors (see [8], [9]).
- This memristor-based TRNG also requires careful coordination of the applied voltage / current flow in order to achieve a given probability distribution.
- a SET-RESET pulse pair is always required to generate each random bit, since the memory elements are non-volatile.
- none of the aforementioned TRNGs can pass all of the standard packages for statistical tests developed by the National Institute of Standards and Technology (NIST 800-22 Test Suite) (see [10]), even if the data is post-processed.
- SC Stochastic computing
- SNG number sequence generator
- CMOS complementary metal-oxide-semiconductor
- SNG silicon technology-based stochastic number generator
- the object is achieved by a device according to claim 1, by a method according to claim 19 and by a computer program according to claim 20.
- the device comprises a switchable element which can be switched to a first state by applying a first bias voltage and which can be switched to a second state by applying a second bias voltage that is different from the first bias voltage.
- the switchable element is designed, when it is switched to the first state by the first bias voltage, to output a first output voltage with a first random or pseudo-random voltage value from a first voltage value range.
- the switchable element is designed, when it is switched to the second state by the second bias voltage, to output a second output voltage with a second random or pseudo-random voltage value from a second voltage value range.
- the device comprises a comparator which is designed to output a first numerical value if the first output voltage from the first value range is less than or equal to a first limit voltage; and if the first output voltage from the first value range is greater than the first limit voltage, to output a second numerical value that is different from the first numerical value.
- the comparator is designed to output the first numerical value if the second output voltage from the second range of values is less than or equal to a second limit voltage, and to output the second numeric value if the second output voltage from the second range of values is greater than the second limit voltage.
- the comparator is designed to output the second numerical value, and if the second output voltage from the second value range is greater than the second limit voltage, to output the first numerical value. Furthermore, a method for generating a sequence of random numbers according to one embodiment is provided.
- the method comprises: applying a first bias voltage to a switchable element in order to switch the switchable element to a first state, or applying a second bias voltage, which is different from the first bias voltage, to the switchable element in order to switch the switchable element into one to switch the second state; wherein the switchable element is designed, when it is switched into the first state by the first bias voltage, to output a first output voltage with a first random or pseudo-random voltage value from a first voltage value range; and wherein the switchable element is designed, when it is switched to the second state by the second bias voltage, to output a second output voltage with a second random or pseudo-random voltage value from a second voltage value range.
- FIG. 1 shows an apparatus for generating a sequence of random numbers according to an embodiment.
- FIG. 2 shows the current-voltage characteristics of an individual cell of a memristive component based on YMO (yttrium manganese oxide) according to one embodiment.
- YMO yttrium manganese oxide
- 3 shows the cycle-to-cycle variation of SET and RESET bias voltages in both positive and negative switching directions of a single YMO memristor cell according to one embodiment.
- 4 shows a YMO memristor cell-based basic module for a real random number generator which can be used as a cryptographic key.
- FIG. 5 shows the distribution of the pulse amplitude of a single YMO memristor cell with 100 cycles as a function of the pulse width.
- FIG. 1 shows an apparatus for generating a sequence of random numbers according to an embodiment.
- the device comprises a switchable element 110 which can be switched to a first state by applying a first bias voltage and which can be switched to a second state by applying a second bias voltage that is different from the first bias voltage.
- the switchable element 110 is designed, when it is switched to the first state by the first bias voltage, to output a first output voltage with a first random or pseudo-random voltage value from a first voltage value range. Furthermore, the switchable element 110 is designed, when it is switched to the second state by the second bias voltage, to output a second output voltage with a second random or pseudo-random voltage value from a second voltage value range.
- the device comprises a comparator 120, which is designed to output a first numerical value if the first output voltage from the first value range is less than or equal to a first limit voltage; and if the first output voltage from the first value range is greater than the first limit voltage, to output a second numerical value that is different from the first numerical value.
- the comparator 120 is designed to output the first numerical value if the second output voltage from the second range of values is less than or equal to a second limit voltage, and to output the second numeric value if the second output voltage from the second range of values is greater than the second limit voltage.
- the comparator 120 is designed to output the second numerical value if the second output voltage from the second range of values is less than or equal to a second limit voltage, and to output the first numeric value if the second output voltage from the second range of values is greater than the second limit voltage .
- the comparator 120 can be designed, for example, to output the first numerical value or the second numerical value as a first output value in a first output step.
- the device for example, can be designed, depending on whether the comparator 120 outputs the first numerical value or the second numerical value, to apply either the first bias voltage or the second bias voltage to the switchable element 110.
- the switchable element 110 can for example be designed to output a further output voltage with a random or pseudo-random voltage value, depending on whether the first bias voltage or the second bias voltage was applied, from the first voltage value range or from the second voltage value range.
- the comparator 120 can be designed, for example, to output the first numerical value or the second numerical value as a second output value as a function of the further output voltage in a second output step.
- the device can furthermore have, for example, a multiplexer, which can be designed, for example, to apply either the first bias voltage or the second bias voltage to the switchable element 110, depending on whether the comparator 120 outputs the first numerical value or the second numerical value.
- a multiplexer which can be designed, for example, to apply either the first bias voltage or the second bias voltage to the switchable element 110, depending on whether the comparator 120 outputs the first numerical value or the second numerical value.
- the switchable element 110 can be, for example, a memristor.
- switchable element 110 may comprise yttrium manganese oxide.
- the switchable element 110 can comprise, for example, bismuth ferrite and / or, for example, bismuth ferrite doped with titanium.
- a largest absolute value of the first voltage range of values can be at least twice as large as a largest absolute value of the second voltage range of values, or the largest absolute value of the second voltage range of values can, for example, be at least twice as large as the largest absolute value of the first voltage value range.
- the largest absolute value of the first voltage range can be, for example, at least four times as large as the largest absolute value of the second voltage range, or the largest absolute value of the second voltage range can be, for example, at least four times as large, like the largest absolute value of the first voltage value range.
- the second limit voltage can be different from the first limit voltage, for example.
- the first limit voltage can be defined, for example, in such a way that a statistical probability that the first output voltage with the first random or pseudo-random voltage value is greater than the first limit voltage has a value between 45% and 55%, and / or that
- the second limit voltage can be defined, for example, in such a way that a statistical probability that the second output voltage coincides with the second is random or pseudo-random Voltage value is greater than the second limit voltage, has a value between 45% and 55%.
- the first limit voltage can be set, for example, such that the statistical probability that the first output voltage with the first random or pseudo-random voltage value is greater than the first limit voltage is 50%, and / or the second limit voltage can, for example, be set in this way be that the statistical probability that the second output voltage with the second random or pseudo-random voltage value is greater than the first limit voltage is 50%.
- the sequence of random numbers can be, for example, a binary sequence of random numbers.
- an output of the first numerical value or the second numerical value by the comparator 120 can correspond to exactly one random number of the binary sequence of random numbers.
- the sequence of random numbers is not a binary sequence of random numbers.
- the device can be designed, for example, to form a random number from the sequence of random numbers using a plurality of numerical values that are output by the comparator 120.
- the device can be designed, for example, to form said random number of the sequence of random numbers using said plurality of numerical values that are output by comparator 120 by adding each of said plurality of numerical values to exactly one binary digit of said random number of said sequence of random numbers forms in binary notation.
- the device may have a current compliance unit that applies a predefined input current to the switchable element 110 when the first bias voltage is applied.
- the device can for example have two or more memristors.
- the plurality of memristors can be arranged, for example, in series, and / or the plurality of memristors can, for example, be arranged in parallel in a line array be arranged, and / or the plurality of memristors can be arranged, for example, in a crossbar array.
- the switchable element 110 can be, for example, a first switchable element 110 and the comparator 120 can be, for example, a first comparator.
- the device can, for example, also have a further switchable element 110 and, for example, a further comparator in order to generate random numbers of the sequence of random numbers.
- the actual polarity and amplitude of the applied write bias voltage are determined by the potential of the upper electrode (T1) and the lower electrode (T2) of the resistance switch.
- the top electrode (T1) can be viewed as a reference for the bias voltage applied to the device. If the potential of the upper electrode is higher than that of the lower electrode, it can be considered a positive voltage applied to the device. Otherwise, if the potential of the lower electrode has a higher potential, it can be considered a negative voltage applied to the device.
- Embodiments provide one or more switchable elements, e.g., one or more memristive components (one or more memristors), for random number generators (RNG).
- memristive components one or more memristors
- RNG random number generators
- the operation of such memristive components is implemented as a true random number generator (TRNG) and as a number sequence generator (SNG).
- a switchable element for example a memristive component (a memristor)
- a memristive component for example a memristor
- the distribution of the responses (output), for example a read current, when asked for "challenges” (input), for example a read voltage can be box-shaped around a probability threshold that is specific for each cell of the memristive component in single-cell, line or Array execution can be distributed.
- the probability of the 0/1 bit stream can be determined, for example, by a probability threshold value.
- the RNG can be used as a TRNG, for example for exchanging keys.
- the RNG can be used as an SNG, for example for stochastic computing.
- the provision of random bit streams using memristive devices with severe hardware and performance constraints can be used for efficient key exchange and for efficient computation of data-intensive problems.
- the use of a memristive component for the construction of TRNGs and SNGs on the basis of an electroforming-free memristor provides an efficient construction which reduces the relative costs considerably.
- the reliable functioning of the RNG under extreme temperatures can be ensured, for example, by a comparable change in the IV characteristics of all cells of the memristive component in single-cell, line or array design.
- Fig. 2 shows current-voltage characteristics (referred to as IV characteristic or IV characteristic) and statistical results for YMO (yttrium manganese oxide), in particular the experimental current-voltage characteristics (IV) of the YMO memristors with the corresponding schematic Images of the memristor stacks.
- FIG. 2 shows the IV characteristics of an individual cell of a memristive component based on YMO on a semilog scale with 100 cycles both in the positive and in the negative direction of the ramp voltage.
- the sizes of the upper contact area are, for example, 0.1 mm 2
- the current compliance (CG) for the SET process is 10 mA.
- the inset illustrates the memristive component schematically.
- the SET and RESET voltages have the same polarity, but different amplitudes.
- a current limitation (CC) is used during the switchover process in order to prevent permanent failure of the device.
- Memristive components with a random variation of the IV characteristics can be used for the realization of RNG.
- FIG. 3 shows in (a) a distribution of the switching biases of a cell of a memristive component based on YMO during
- the current conformity for the SET process in the YMO memristive component is, for example, 10 mA.
- the sizes of the upper contact area are 0.1 mm2.
- the pulse width tp 10 ms.
- the insets show the corresponding histograms. 3 shows the cycle-to-cycle variation of SET and RESET bias voltages in both positive (225 cycles) and negative (1082 cycles) switching directions of a single YMO memristor cell.
- the width of the distribution was modeled with a Gaussian function with a large half-width.
- a single cell of a memristive component based on YMO is provided for the implementation of a TRNG.
- the SET and RESET distortions with a cumulative probability of 50% are selected as source distortions in the block design of TRNG as VSET and VRESET for receiving the Hamming distance between the classes of 50%.
- the operation of memristive components on the basis of YMO can be provided as TRNG and SNG.
- TRNG for example, both stochastic and safe properties may be required.
- 4 shows a memristive component based on YMO for a true random number generator.
- the random number generator can be used for a cryptographic key.
- 4 further illustrates the working principle of a YMO as a TRNG using a specific example.
- the structure of FIG. 4 does not require a read bias.
- FIG. 4 shows a YMO memristor cell 110, a multiplexer 130, a comparator 120 and a current limiting unit CG (also referred to as current compliance unit CC).
- a fixed width SET bias V SET is applied to a YMO memristor cell 110 and a series resistor Rs. If the YMO memristor cell 110 is switched on under the applied (bias) voltage and thus the output voltage across the series resistor Rs Icc ⁇ Rs is higher than the precisely defined reference voltage of the comparator 120 V ref , the output voltage of the comparator goes to high logic level, therefore the output of comparator 120 is "logic-1".
- Icc is the match level current of the YMO device.
- V ref Icc * RS-V OFFSET applies .
- V OFFSET has a small constant value, e.g. 0.001 V, which is not related to the dynamics of YMO cells.
- VRESET is selected by multiplexer 130 in accordance with the feedback "1" from the output of comparator 120 in the previous cycle and applied to YMO memristor cell 110 in order to reset the cell to HRS.
- the voltages VRs in HRS are lower than V ref .
- the output of the comparator 120 is “logic-0” in this case.
- the pulse width and amplitude of the SET / RESET processes are determined based on a statistical investigation.
- V ref Icc ⁇ Rs-V0
- CMOS-based stochastic circuits consist of SNG conversion sources and arithmetic logic gates. SNGs are essential components for memristive implementations of SC circuits. The high resource consumption of conventional SNGs developed in CMOS technology is reduced, for example, by the exemplary device in FIG. 4. The inherently stochastic YMO memristor cells are proposed here in order to implement the inexpensive SNG.
- FIG. 5 shows the distribution of the pulse amplitude of a single YMO memristor cell with 100 cycles as a function of the pulse width (100 ms, 200 ms, 500 ms, 1000 ms) in SET and RESET.
- a Poisson distribution with a large half-width is observed, the mean value of which for SET shifts to lower voltages with increasing pulse width.
- the 0/1 probability distribution can be set over the pulse width [13-14]).
- the stochastic switching behavior of the YMO-based memristor cell can be controlled, i.e. the output with probabilities can be realized with different pulse widths or pulse amplitudes.
- the stochastic switching behavior of the YMO-based memristor cell can be controlled, i.e. the output with probabilities can be realized with different pulse widths or pulse amplitudes.
- a sequence number generator (SNG; number sequence generator) can be implemented with a single, electroforming-free, unipolar memristor without an electroforming step.
- the memristor can have a stochastic current-voltage characteristic, that is, the read current Ir can, for example, for a given write voltage Uw, write pulse length tw and read voltage Ur happen to be below or above a threshold value.
- HRS High Resistance State
- LRS Low Resistance State
- the reference value for the memristor can be established.
- the write pulse length tp can determine the probability of the sequence number generator (SNG) as a function of the write voltage (negative, positive, URESET, USET).
- the write pulse length can be selected internally at random, and thus, for example, the probability of the sequence number generator can be selected at random.
- SNG sequence number generators
- the (N) memristors of the (N) sequence number generators can be designed with a common unstructured or a structured rear electrode and in series or in series and / or in parallel in a line array or in a crossbar Array be arranged.
- each of the N memristors can have a stochastic current-voltage characteristic, whereby, for example, the read current Ir for a given write voltage Uw, write pulse length tw and read voltage Ur can be randomly below or above a threshold value.
- (N) reference values can be established for each of the (N) memristors.
- the write pulse length tp of each of the (N) memristors can determine the probability of the sequence number generator (SNG) of each of the (N) memristors as a function of the write voltage Uw (negative, positive, URESET, USET).
- SNG sequence number generator
- the write pulse length tp of each of the (N) memristors can be selected internally at random, with the probability of the sequence number generator of each of the (N) memristors being able to be selected randomly.
- the key exchange for example, can be shown as an application example.
- a true random number generator with a threshold value of 50:50 can be used for this.
- stochastic computing with a sequence number generator can be provided, for example,
- aspects have been described in connection with a device, it goes without saying that these aspects also represent a description of the corresponding method, so that a block or a component of a device is also to be understood as a corresponding method step or as a feature of a method step. Analogously to this, aspects that have been described in connection with or as a method step also represent a description of a corresponding block or details or features of a corresponding device.
- Some or all of the method steps can be carried out by a hardware apparatus (or using a hardware Apparatus), such as a microprocessor, a programmable computer or electronic circuit. In some embodiments, some or more of the most important process steps can be performed by such an apparatus.
- exemplary embodiments of the invention can be implemented in hardware or in software or at least partially in hardware or at least partially in software.
- the implementation can be carried out using a digital storage medium, for example a floppy disk, a DVD, a BluRay disk, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, a hard disk or some other magnetic or optical memory Memory are carried out on the electronically readable control signals are stored, which can interact with a programmable computer system or cooperate in such a way that the respective method is carried out. Therefore, the digital storage medium can be computer readable.
- Some exemplary embodiments according to the invention thus comprise a data carrier which has electronically readable control signals which are able to interact with a programmable computer system in such a way that one of the methods described herein is carried out.
- exemplary embodiments of the present invention can be implemented as a computer program product with a program code, the program code being effective to carry out one of the methods when the computer program product runs on a computer.
- the program code can, for example, also be stored on a machine-readable carrier.
- an exemplary embodiment of the method according to the invention is thus a computer program which has a program code for performing one of the methods described herein when the computer program runs on a computer.
- a further exemplary embodiment of the method according to the invention is thus a data carrier (or a digital storage medium or a computer-readable medium) on which the computer program for performing one of the methods described herein is recorded.
- the data carrier or the digital storage medium or the computer-readable medium are typically tangible and / or non-transitory.
- a further exemplary embodiment of the method according to the invention is thus a data stream or a sequence of signals which represents or represents the computer program for performing one of the methods described herein.
- the data stream or the sequence of signals can, for example, be configured to be transferred via a data communication connection, for example via the Internet.
- Another exemplary embodiment comprises a processing device, for example a computer or a programmable logic component, which is configured or adapted to carry out one of the methods described herein.
- a processing device for example a computer or a programmable logic component, which is configured or adapted to carry out one of the methods described herein.
- Another exemplary embodiment comprises a computer on which the computer program for performing one of the methods described herein is installed.
- a further exemplary embodiment according to the invention comprises a device or a system which is designed to transmit a computer program for carrying out at least one of the methods described herein to a receiver.
- the transmission can take place electronically or optically, for example.
- the receiver can be, for example, a computer, a mobile device, a storage device or a similar device.
- the device or the system can, for example, comprise a file server for transmitting the computer program to the recipient.
- a programmable logic component for example a field-programmable gate array, an FPGA
- FPGA field-programmable gate array
- a field-programmable gate array can interact with a microprocessor in order to carry out one of the methods described herein.
- the methods are performed by any hardware device. This can be a universally replaceable one Hardware such as a computer processor (CPU) or hardware specific to the method such as an ASIC.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Electronic Switches (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102020206790.2A DE102020206790A1 (de) | 2020-05-29 | 2020-05-29 | Vorrichtung und Verfahren zur Hardware-basierten Zufallszahlen- und Zahlenfolgen-Generierung |
| PCT/EP2021/064222 WO2021239886A1 (de) | 2020-05-29 | 2021-05-27 | Vorrichtung und verfahren zur hardware-basierten zufallszahlen- und zahlenfolgen-generierung |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4158464A1 true EP4158464A1 (de) | 2023-04-05 |
Family
ID=76250334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21729485.9A Pending EP4158464A1 (de) | 2020-05-29 | 2021-05-27 | Vorrichtung und verfahren zur hardware-basierten zufallszahlen- und zahlenfolgen-generierung |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230090726A1 (de) |
| EP (1) | EP4158464A1 (de) |
| DE (1) | DE102020206790A1 (de) |
| WO (1) | WO2021239886A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102022125361A1 (de) | 2022-09-30 | 2024-04-04 | TechIFab GmbH | Vorrichtungen und verfahren zum betreiben eines memristiven bauelements |
| DE102022125356A1 (de) * | 2022-09-30 | 2024-04-04 | TechIFab GmbH | Vorrichtungen und verfahren zum betreiben eines memristiven bauelements |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10217046B2 (en) | 2015-06-29 | 2019-02-26 | International Business Machines Corporation | Neuromorphic processing devices |
| GB2548081B (en) | 2016-02-23 | 2019-10-02 | Univ Oxford Brookes | Logic gate |
| ITUA20161468A1 (it) * | 2016-03-08 | 2017-09-08 | Milano Politecnico | Dispositivo e metodo per generare numeri casuali |
| US10708041B2 (en) | 2017-04-30 | 2020-07-07 | Technion Research & Development Foundation Limited | Memresistive security hash function |
-
2020
- 2020-05-29 DE DE102020206790.2A patent/DE102020206790A1/de active Pending
-
2021
- 2021-05-27 EP EP21729485.9A patent/EP4158464A1/de active Pending
- 2021-05-27 WO PCT/EP2021/064222 patent/WO2021239886A1/de not_active Ceased
-
2022
- 2022-11-29 US US18/059,530 patent/US20230090726A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021239886A1 (de) | 2021-12-02 |
| US20230090726A1 (en) | 2023-03-23 |
| DE102020206790A1 (de) | 2021-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102004047425B4 (de) | Zufallszahlengenerator sowie Verfahren zur Erzeugung von Zufallszahlen | |
| DE102020107174A1 (de) | Selbstheilende dot-product engine | |
| Lin et al. | Physical realization of a supervised learning system built with organic memristive synapses | |
| DE112020000929T5 (de) | Programmieren eines phasenwechselspeichersin einer geschlossenen schleife | |
| DE102019116407B4 (de) | Realisierung neuronaler netze mit ternären eingängen und binären gewichten in nand-speicherarrays | |
| Hu et al. | The stochastic modeling of TiO 2 memristor and its usage in neuromorphic system design | |
| WO2021239886A1 (de) | Vorrichtung und verfahren zur hardware-basierten zufallszahlen- und zahlenfolgen-generierung | |
| CN113887713B (zh) | 包括单硅器件的尖脉冲发生电路 | |
| DE102010024622A1 (de) | Identifikationsschaltung und Verfahren zum Erzeugen eines Identifikationsbits | |
| KR102499691B1 (ko) | 단일 게이트의 피드백 전계효과 전자소자를 이용하는 축적 및 발화 뉴런회로 | |
| Ahmadi-Farsani et al. | A CMOS–memristor hybrid system for implementing stochastic binary spike timing-dependent plasticity | |
| DE112012005565T5 (de) | Elektronische Synapsen aus stochastischen binären Speichereinheiten | |
| Saxena | High LRS-resistance CMOS memristive synapses for energy-efficient neuromorphic SoCs | |
| Ntinas et al. | Memristor-based probabilistic cellular automata | |
| DE102021105181A1 (de) | Vorrichtung und verfahren zum lesen von daten in einem speicher | |
| Cipollini et al. | Conduction and entropy analysis of a mixed memristor-resistor model for neuromorphic networks | |
| Wouters et al. | Reliability of computing-in-memory concepts based on memristive arrays | |
| DE112021004941T5 (de) | Gewichtungswiederholung in rpu-kreuzschienen-arrays | |
| Sahay et al. | Hybrid CMOS-OxRAM RNG Circuits | |
| EP4158840B1 (de) | Vorrichtung und verfahren zur erzeugung von hardware-basierten physikalisch nicht klonbaren funktionen und deren verwendung | |
| DE102020206796A1 (de) | Memristor-basierte Volladdierer und Verfahren zu deren Betrieb | |
| Wu et al. | Enabling bio-plausible multi-level stdp using cmos neurons with dendrites and bistable rrams | |
| Xu et al. | Analog memristor based neuromorphic crossbar circuit for image recognition | |
| DE102019119744A1 (de) | Konfigurierbares präzises neuronales netz mit differentieller binärer, nichtflüchtiger speicherzellenstruktur | |
| Nielen et al. | Memristive Sorting Networks Enabled by Electrochemical Metallization Cells. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20221125 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20251218 |