A functional MOS transistor featuring gate-level weighted sum and threshold operations

A functional MOS transistor is proposed which works more intelligently than a mere switching device. The functional transistor calculates the weighted sum of all input signals at the gate level, and controls the 'on' and 'off' of the transistor based on the result of such a weighted sum operation. Since the function is quite analogous to that of biological neurons, the device is named a neuron MOSFET, or neuMOS (vMOS). The device is composed of a floating gate and multiples of input gates that capacitively interact with the floating gate. As the gate-level sum operation is performed in a voltage mode utilizing the capacitive coupling effect, essentially no power dissipation occurs in the calculation, making the device ideal for ULSI implementation. The basic characteristics of neuron MOSFETs as well as of simple circuit blocks are analyzed based on a simple transistor model and experiments. Making use of its very powerful function, a number of interesting circuit applications are explored. A soft hardware logic circuit implemented by neuMOS transistors is also proposed. >

[1]  Tadahiro Ohmi,et al.  Future trends and applications of ultra-clean technology , 1989, International Technical Digest on Electron Devices Meeting.

[2]  Daniel Etiemble,et al.  Comparison of binary and multivalued ICs according to VLSI criteria , 1988, Computer.

[3]  T. Shibata,et al.  An optimally designed process for submicrometer MOSFET's , 1982 .

[4]  Tadahiro Ohmi,et al.  A self-learning neural-network LSI using neuron MOSFETs , 1992, 1992 Symposium on VLSI Technology Digest of Technical Papers.

[5]  Tadashi Shibata,et al.  Neuron MOS binary-logic integrated circuits. I. Design fundamentals and soft-hardware-logic circuit implementation , 1993 .

[6]  K. Taniguchi,et al.  Time-dependent-dielectric breakdown of thin thermally grown SiO2films , 1985, IEEE Transactions on Electron Devices.

[7]  Kenneth C. Smith.  The Prospects for Multivalued Logic: A Technology and Applications View , 1981, IEEE Transactions on Computers.

[8]  R.H. Dennard,et al.  1 µm MOSFET VLSI technology: Part IV—Hot-electron design constraints , 1979, IEEE Transactions on Electron Devices.

[9]  G. Baccarani,et al.  Generalized scaling theory and its application to a ¼ micrometer MOSFET design , 1984, IEEE Transactions on Electron Devices.

[10]  Tadahiro Ohmi,et al.  An intelligent MOS transistor featuring gate-level weighted sum and threshold operations , 1991, International Electron Devices Meeting 1991 [Technical Digest].

[11]  T. Hanyu,et al.  Design of a highly parallel AI processor using new multiple-valued MOS devices , 1988, [1988] Proceedings. The Eighteenth International Symposium on Multiple-Valued Logic.

[12]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[13]  W. Fichtner,et al.  Generalized guide for MOSFET miniaturization , 1980, IEEE Electron Device Letters.

[14]  T. Shibata,et al.  A New EEPROM Cell with Dual Control Gate Structure , 1983, 1983 Symposium on VLSI Technology. Digest of Technical Papers.

[15]  Shoji Kawahito,et al.  A multiplier chip with multiple-valued bidirectional current-mode logic circuits , 1988, Computer.

[16]  Michitaka Kameyama,et al.  Design and implementation of quaternary NMOS integrated circuits for pipelined image processing , 1987 .

[17]  S. Inoue,et al.  Optimum design of dual-control gate cell for high-density EEPROM's , 1983, IEEE Transactions on Electron Devices.

[18]  S. Kawahito,et al.  VLSI-oriented bi-directional current-mode arithmetic circuits based on the Radix-4 signed-digit number system , 1986 .

[19]  Kenneth C. Smith,et al.  A multiple valued logic: a tutorial and appreciation , 1988, Computer.