JP7329151B2 - 人工ニューラルネットワーク内のアナログニューラルメモリにおけるデータドリフトを補償するための回路 - Google Patents
人工ニューラルネットワーク内のアナログニューラルメモリにおけるデータドリフトを補償するための回路 Download PDFInfo
- Publication number
- JP7329151B2 JP7329151B2 JP2022540418A JP2022540418A JP7329151B2 JP 7329151 B2 JP7329151 B2 JP 7329151B2 JP 2022540418 A JP2022540418 A JP 2022540418A JP 2022540418 A JP2022540418 A JP 2022540418A JP 7329151 B2 JP7329151 B2 JP 7329151B2
- Authority
- JP
- Japan
- Prior art keywords
- circuit
- array
- current
- output
- cell
- 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.)
- Active
Links
- 230000015654 memory Effects 0.000 title claims description 205
- 238000013528 artificial neural network Methods 0.000 title description 36
- 230000001537 neural effect Effects 0.000 title description 18
- 239000013598 vector Substances 0.000 claims description 53
- 238000000034 method Methods 0.000 claims description 40
- 239000003990 capacitor Substances 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000005689 Fowler Nordheim tunneling Effects 0.000 claims description 3
- 239000000654 additive Substances 0.000 claims 1
- 230000000996 additive effect Effects 0.000 claims 1
- 210000004027 cell Anatomy 0.000 description 346
- 210000002569 neuron Anatomy 0.000 description 70
- 230000006870 function Effects 0.000 description 62
- 238000007667 floating Methods 0.000 description 35
- 210000000225 synapse Anatomy 0.000 description 31
- 238000003491 array Methods 0.000 description 29
- 230000004913 activation Effects 0.000 description 25
- 230000010354 integration Effects 0.000 description 12
- 239000000463 material Substances 0.000 description 10
- 238000012937 correction Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 239000000758 substrate Substances 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 102100036301 C-C chemokine receptor type 7 Human genes 0.000 description 6
- 102100031658 C-X-C chemokine receptor type 5 Human genes 0.000 description 6
- 101000716065 Homo sapiens C-C chemokine receptor type 7 Proteins 0.000 description 6
- 101000922405 Homo sapiens C-X-C chemokine receptor type 5 Proteins 0.000 description 6
- 230000002093 peripheral effect Effects 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 4
- 230000000946 synaptic effect Effects 0.000 description 4
- 230000000295 complement effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 239000010703 silicon Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 150000004767 nitrides Chemical class 0.000 description 2
- 230000005641 tunneling Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 102100023226 Early growth response protein 1 Human genes 0.000 description 1
- 101001049697 Homo sapiens Early growth response protein 1 Proteins 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000002784 hot electron Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/065—Analogue means
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/10—Programming or data input circuits
- G11C16/14—Circuits for erasing electrically, e.g. erase voltage switching circuits
- G11C16/16—Circuits for erasing electrically, e.g. erase voltage switching circuits for erasing blocks, e.g. arrays, words, groups
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
- G11C16/349—Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/02—Digital function generators
- G06F1/03—Digital function generators working, at least partly, by table look-up
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/1666—Error detection or correction of the data by redundancy in hardware where the redundant component is memory or memory area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F7/76—Arrangements for rearranging, permuting or selecting data according to predetermined rules, independently of the content of the data
- G06F7/78—Arrangements for rearranging, permuting or selecting data according to predetermined rules, independently of the content of the data for changing the order of data flow, e.g. matrix transposition or LIFO buffers; Overflow or underflow handling therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/54—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using elements simulating biological cells, e.g. neuron
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/56—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency
- G11C11/5621—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency using charge storage in a floating gate
- G11C11/5628—Programming or writing circuits; Data input circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/56—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency
- G11C11/5621—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency using charge storage in a floating gate
- G11C11/5628—Programming or writing circuits; Data input circuits
- G11C11/5635—Erasing circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
- G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
- G11C13/0021—Auxiliary circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/04—Erasable programmable read-only memories electrically programmable using variable threshold transistors, e.g. FAMOS
- G11C16/0408—Erasable programmable read-only memories electrically programmable using variable threshold transistors, e.g. FAMOS comprising cells containing floating gate transistors
- G11C16/0425—Erasable programmable read-only memories electrically programmable using variable threshold transistors, e.g. FAMOS comprising cells containing floating gate transistors comprising cells containing a merged floating gate and select transistor
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/10—Programming or data input circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/24—Bit-line control circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/26—Sensing or reading circuits; Data output circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
- G11C16/3404—Convergence or correction of memory cell threshold voltages; Repair or recovery of overerased or overprogrammed cells
- G11C16/3413—Circuits or methods to recover overprogrammed nonvolatile memory cells detected during program verification, usually by means of a "soft" erasing step
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
- G11C16/3436—Arrangements for verifying correct programming or erasure
- G11C16/3454—Arrangements for verifying correct programming or for detecting overprogrammed cells
- G11C16/3459—Circuits or methods to verify correct programming of nonvolatile memory cells
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
- G11C16/3436—Arrangements for verifying correct programming or erasure
- G11C16/3454—Arrangements for verifying correct programming or for detecting overprogrammed cells
- G11C16/3463—Circuits or methods to detect overprogrammed nonvolatile memory cells, usually during program verification
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
- G11C16/3436—Arrangements for verifying correct programming or erasure
- G11C16/3468—Prevention of overerasure or overprogramming, e.g. by verifying whilst erasing or writing
- G11C16/3486—Circuits or methods to prevent overprogramming of nonvolatile memory cells, e.g. by detecting onset or cessation of current flow in cells and using the detector output to terminate programming
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C27/00—Electric analogue stores, e.g. for storing instantaneous values
- G11C27/005—Electric analogue stores, e.g. for storing instantaneous values with non-volatile charge storage, e.g. on floating gate or MNOS
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/02—Detection or location of defective auxiliary circuits, e.g. defective refresh counters
- G11C29/021—Detection or location of defective auxiliary circuits, e.g. defective refresh counters in voltage or current generators
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/02—Detection or location of defective auxiliary circuits, e.g. defective refresh counters
- G11C29/028—Detection or location of defective auxiliary circuits, e.g. defective refresh counters with adaption or trimming of parameters
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
- G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
- G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
- G11C29/44—Indication or identification of errors, e.g. for repair
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Neurology (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Non-Volatile Memory (AREA)
- Read Only Memory (AREA)
- Semiconductor Memories (AREA)
- Error Detection And Correction (AREA)
- Networks Using Active Elements (AREA)
- Feedback Control In General (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Complex Calculations (AREA)
Description
本出願は、2020年1月3日に出願された「Precise Data Tuning Method and Apparatus for Analog Neuromorphic Memory in an Artificial Neural Network」と題する米国仮特許出願第62/957,013号、及び2020年3月26日に出願された「Circuitry to Compensate for Data Drift in Analog Neural Memory in an Artificial Neural Network」と題する米国特許出願第16/830,733号の優先権を主張する。
アナログニューロモーフィックメモリシステム内のVMMアレイ内の不揮発性メモリセルにおけるドリフト誤差を補償するための多数の実施形態が提供される。
<不揮発性メモリセル>
表1:図2のフラッシュメモリセル210の動作
表2:図4のフラッシュメモリセル410の動作
表3:図6のフラッシュメモリセル610の動作
<不揮発性メモリセルアレイを使用するニューラルネットワーク>
<VMMアレイ>
Ids=Io*e(Vg-Vth)/nVt=w*Io*e(Vg)/nVt
式中、w=e(-Vth)/nVtであり、
式中、Idsは、ドレイン-ソース間電流であり、Vgは、メモリセルのゲート電圧であり、Vthは、メモリセルのスレッショルド電圧であり、Vtは、熱電圧=k*T/qであり、kは、ボルツマン定数、Tは、ケルビン温度、qは、電子電荷であり、nは、傾斜係数=1+(Cdep/Cox)であり、Cdep=空乏層の容量、及びCoxは、ゲート酸化物層の容量であり、Ioは、スレッショルド電圧に等しいゲート電圧におけるメモリセル電流であり、Ioは、(Wt/L)*u*Cox*(n-1)*Vt2に比例し、式中、uは、キャリア移動度であり、Wt及びLはそれぞれ、メモリセルの幅及び長さである。
Vg=n*Vt*log[Ids/wp*Io]
式中、wpは、基準又は周辺メモリセルのwである。
Vg=n*Vt*log[Ids/wp*Io]
Iout=wa*Io*e(Vg)/nVt、すなわち
Iout=(wa/wp)*Iin=W*Iin
W=e(Vthp-Vtha)/nVt
Iin=wp*Io*e(Vg)/nVt
式中、メモリアレイの各メモリセルのwa=wである。
Ids=ベータ*(Vgs-Vth)*Vds; ベータ=u*Cox*Wt/L
W α (Vgs-Vth)
すなわち、直線領域における重みWは、(Vgs-Vth)に比例する。
Ids=1/2*ベータ*(Vgs-Vth)2; ベータ=u*Cox*Wt/L
W α (Vgs-Vth)2、すなわち重みWは、(Vgs-Vth)2に比例する。
表5:図12のVMMアレイ1200の動作
表6:図13のVMMアレイ1300の動作
表7:図14のVMMアレイ1400の動作
表8:図15のVMMアレイ1500の動作
<長・短期メモリ>
<ゲート付き回帰型ユニット>
<VMM内のセルの正確なチューニングのための実施形態>
表9:重みチューニング方法
したがって、VOUTPUTは、データドリフトを補償するための、VINPUTのスケーリング及びシフトされたバージョンである。
表10:フラッシュメモリセルの動作
Claims (24)
- ベクトル行列乗算アレイにおける読み出し動作中にドリフト誤差を補償するための回路であって、前記回路が、
データドリフトを示す出力を生成するために、前記アレイに結合されたデータドリフト監視回路と、
前記データドリフト監視回路からの前記出力に応答して補償電流を生成し、前記補償電流を前記アレイの1つ以上のビット線に注入するためのビット線補償回路と、を備える、回路。 - 前記ビット線補償回路が、第1の調整可能な電流源及び第2の調整可能な電流源を備え、前記補償電流が、前記第1の調整可能な電流源によって生成された電流と、前記第2の調整可能な電流源によって生成された電流との間の差である、請求項1に記載の回路。
- 前記ビット線補償回路が、演算増幅器、第1の調整可能な抵抗器、及び第2の調整可能な抵抗器を備える、請求項1に記載の回路。
- 前記ビット線補償回路が、演算増幅器、電流源、及び調整可能なコンデンサを備える、請求項1に記載の回路。
- 前記ビット線補償回路が、M:N電流ミラーを備える、請求項1に記載の回路。
- 前記ビット線補償回路が、演算増幅器、第1の調整可能な抵抗器、第2の調整可能な抵抗器、及び第3の調整可能な抵抗器を備える、請求項1に記載の回路。
- 前記ビット線補償回路が、演算増幅器、電流源、電流シフタ、及び調整可能なコンデンサを備える、請求項1に記載の回路。
- ベクトル行列乗算アレイにおける読み出し動作中にドリフト誤差を補償するための回路であって、前記回路が、
補償電流を生成し、前記補償電流を前記アレイの1つ以上のビット線に注入してドリフト誤差を補償するためのビット線補償回路を備える、回路。 - 前記ビット線補償回路が、加算的補償電流を備える、請求項8に記載の回路。
- 前記ビット線補償回路が、減算的補償電流を含む、請求項8に記載の回路。
- 前記ベクトル行列乗算アレイが、スプリットゲート不揮発性メモリセルから形成される、請求項8に記載の回路。
- ベクトル行列乗算アレイにおける読み出し動作中にドリフト誤差を補償するための回路であって、前記回路が、
前記アレイの出力をスケーリングしてドリフト誤差を補償するためのビット線補償回路と、を備える、回路。 - 前記ビット線補償回路が、前記出力をシフトさせる、請求項12に記載の回路。
- 前記スケーリングが、上方スケーリングを含む、請求項12に記載の回路。
- 前記スケーリングが、下方スケーリングを含む、請求項12に記載の回路。
- 前記スケーリングが、2つの抵抗器の比によって決定される、請求項12に記載の回路。
- 前記スケーリングが、2つのコンデンサの比によって決定される、請求項12に記載の回路。
- 前記ベクトル行列乗算アレイが、スプリットゲート不揮発性メモリセルから形成される、請求項12に記載の回路。
- ベクトル行列乗算アレイにおける読み出し動作中にドリフト誤差を補償するための回路であって、前記回路が、
前記アレイの出力をシフトしてドリフト誤差を補償するためのビット線補償回路、を備える、回路。 - 前記ベクトル行列乗算アレイが、スプリットゲート不揮発性メモリセルから形成される、請求項19に記載の回路。
- 前記ベクトル行列乗算アレイ内の1つ以上のセルが、ファウラーノルドハイムトンネリングを使用してプログラムされている、請求項19に記載の回路。
- 前記ベクトル行列乗算アレイ内の1つ以上のセルが、ファウラーノルドハイムトンネリングを使用してプログラムされている、請求項20に記載の回路。
- ベクトル行列乗算アレイにおける読み出し動作中にドリフト誤差を補償する方法であって、前記方法が、
前記ベクトル行列乗算アレイにおけるデータドリフトを監視するステップと、
前記データドリフトに応答してビット線補償電流を生成するステップと、
読み出し動作中に前記ビット線補償電流を前記ベクトル行列乗算アレイの1つ以上のビット線に注入して、ドリフト誤差を補償するステップと、を含む、方法。 - 前記ベクトル行列乗算アレイが、スプリットゲート不揮発性メモリセルから形成される、請求項23に記載の方法。
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202062957013P | 2020-01-03 | 2020-01-03 | |
US62/957,013 | 2020-01-03 | ||
US16/830,733 US20210209457A1 (en) | 2020-01-03 | 2020-03-26 | Circuitry to compensate for data drift in analog neural memory in an artificial neural network |
US16/830,733 | 2020-03-26 | ||
PCT/US2020/049235 WO2021137900A1 (en) | 2020-01-03 | 2020-09-03 | Circuitry to compensate for data drift in analog neural memory in an artificial neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2023509636A JP2023509636A (ja) | 2023-03-09 |
JP7329151B2 true JP7329151B2 (ja) | 2023-08-17 |
Family
ID=76654025
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2022540417A Active JP7404542B2 (ja) | 2020-01-03 | 2020-07-02 | 人工ニューラルネットワークにおけるアナログニューラルメモリのための精密なデータ調整方法及び装置 |
JP2022540418A Active JP7329151B2 (ja) | 2020-01-03 | 2020-09-03 | 人工ニューラルネットワーク内のアナログニューラルメモリにおけるデータドリフトを補償するための回路 |
JP2023209950A Pending JP2024028955A (ja) | 2020-01-03 | 2023-12-13 | 人工ニューラルネットワークにおけるアナログニューラルメモリのための精密なデータ調整方法及び装置 |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2022540417A Active JP7404542B2 (ja) | 2020-01-03 | 2020-07-02 | 人工ニューラルネットワークにおけるアナログニューラルメモリのための精密なデータ調整方法及び装置 |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2023209950A Pending JP2024028955A (ja) | 2020-01-03 | 2023-12-13 | 人工ニューラルネットワークにおけるアナログニューラルメモリのための精密なデータ調整方法及び装置 |
Country Status (7)
Country | Link |
---|---|
US (3) | US11636322B2 (ja) |
EP (2) | EP4085461B1 (ja) |
JP (3) | JP7404542B2 (ja) |
KR (2) | KR20220104004A (ja) |
CN (2) | CN114930458A (ja) |
TW (3) | TWI785435B (ja) |
WO (2) | WO2021137894A1 (ja) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11475946B2 (en) * | 2020-01-16 | 2022-10-18 | International Business Machines Corporation | Synapse weight update compensation |
US11532354B2 (en) * | 2020-03-22 | 2022-12-20 | Silicon Storage Technology, Inc. | Precision tuning of a page or word of non-volatile memory cells and associated high voltage circuits for an analog neural memory array in an artificial neural network |
US11514326B2 (en) * | 2020-06-18 | 2022-11-29 | International Business Machines Corporation | Drift regularization to counteract variation in drift coefficients for analog accelerators |
US11335401B1 (en) * | 2021-01-28 | 2022-05-17 | National Tsing Hua University | Memory unit with multiple word lines for nonvolatile computing-in-memory applications and current calibrating method thereof |
CN113392591B (zh) * | 2021-07-12 | 2022-04-19 | 哈尔滨工程大学 | 一种基于硅微结构分析的mems加速度计温漂误差估计方法 |
US11935603B2 (en) * | 2021-11-04 | 2024-03-19 | Infineon Technologies LLC | Erase power loss indicator (EPLI) implementation in flash memory device |
US11942144B2 (en) | 2022-01-24 | 2024-03-26 | Stmicroelectronics S.R.L. | In-memory computation system with drift compensation circuit |
TWI833192B (zh) * | 2022-03-31 | 2024-02-21 | 國立陽明交通大學 | 電漿放電電流分類系統及方法 |
WO2023196000A1 (en) * | 2022-04-07 | 2023-10-12 | Silicon Storage Technology, Inc. | Vector-by-matrix-multiplication array utilizing analog inputs |
US11894052B2 (en) | 2022-04-12 | 2024-02-06 | Stmicroelectronics S.R.L. | Compensated analog computation for an in-memory computation system |
EP4390934A1 (en) * | 2022-12-23 | 2024-06-26 | STMicroelectronics S.r.l. | In-memory computation device having improved drift compensation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030128567A1 (en) | 2002-01-07 | 2003-07-10 | Chih-Kang Chiu | Sensing apparatus for a ROM memory device |
JP2006114078A (ja) | 2004-10-12 | 2006-04-27 | Toshiba Corp | 不揮発性半導体記憶装置及びその動作方法 |
US20110122684A1 (en) | 2009-11-20 | 2011-05-26 | Industrial Technology Research Institute | Voltage compensation circuit, multi-level memory device with the same, and voltage compensation method for reading the multi-level memory device |
Family Cites Families (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5029130A (en) | 1990-01-22 | 1991-07-02 | Silicon Storage Technology, Inc. | Single transistor non-valatile electrically alterable semiconductor memory device |
JPH08249893A (ja) * | 1995-03-07 | 1996-09-27 | Toshiba Corp | 半導体記憶装置 |
WO2002059706A2 (en) * | 2001-01-26 | 2002-08-01 | True Circuits, Inc. | Programmable current mirror |
US6747310B2 (en) | 2002-10-07 | 2004-06-08 | Actrans System Inc. | Flash memory cells with separated self-aligned select and erase gates, and process of fabrication |
US7193898B2 (en) * | 2005-06-20 | 2007-03-20 | Sandisk Corporation | Compensation currents in non-volatile memory read operations |
EP1865398A1 (en) * | 2006-06-07 | 2007-12-12 | Patent-Treuhand-Gesellschaft für elektrische Glühlampen mbH | A temperature-compensated current generator, for instance for 1-10V interfaces |
US7551028B1 (en) * | 2006-12-11 | 2009-06-23 | Marvell International Ltd. | Signal generators for current-mode three-level digital amplifiers |
KR100843144B1 (ko) * | 2006-12-20 | 2008-07-02 | 삼성전자주식회사 | 저항체를 이용한 비휘발성 메모리 장치 및 그 구동 방법 |
KR100891005B1 (ko) * | 2007-06-28 | 2009-03-31 | 삼성전자주식회사 | 고온 스트레스로 인한 읽기 마진의 감소를 보상하기 위한플래시 메모리 장치 및 그것의 읽기 전압 조정 방법 |
KR20100074667A (ko) * | 2008-12-24 | 2010-07-02 | 주식회사 하이닉스반도체 | 플래시 메모리 장치의 동작 방법 |
US7928784B2 (en) * | 2009-06-26 | 2011-04-19 | Texas Instruments Incorporated | Method and apparatus to improve and control the propagation delay in a current slewing circuit |
US8779777B2 (en) * | 2010-06-04 | 2014-07-15 | Linear Technology Corporation | Dynamic compensation of aging drift in current sense resistor |
US9490023B2 (en) * | 2014-03-19 | 2016-11-08 | Apple Inc. | Mitigation of retention drift in charge-trap non-volatile memory |
WO2017200883A1 (en) | 2016-05-17 | 2017-11-23 | Silicon Storage Technology, Inc. | Deep learning neural network classifier using non-volatile memory array |
US10346740B2 (en) | 2016-06-01 | 2019-07-09 | Kla-Tencor Corp. | Systems and methods incorporating a neural network and a forward physical model for semiconductor applications |
US10340010B2 (en) * | 2016-08-16 | 2019-07-02 | Silicon Storage Technology, Inc. | Method and apparatus for configuring array columns and rows for accessing flash memory cells |
EP3577689A4 (en) * | 2017-02-04 | 2021-06-02 | Monolithic 3D Inc. | 3D SEMICONDUCTOR COMPONENT AND STRUCTURE |
KR102532204B1 (ko) * | 2017-09-15 | 2023-05-16 | 삼성전자 주식회사 | 레퍼런스 셀을 포함하는 저항성 메모리 장치 및 그것의 동작 방법 |
US10510393B2 (en) * | 2017-09-15 | 2019-12-17 | Samsung Electronics Co., Ltd | Resistive memory device including reference cell and operating method thereof |
US10748630B2 (en) | 2017-11-29 | 2020-08-18 | Silicon Storage Technology, Inc. | High precision and highly efficient tuning mechanisms and algorithms for analog neuromorphic memory in artificial neural networks |
US10504587B2 (en) * | 2017-12-20 | 2019-12-10 | Intel Corporation | Method and system for compensating for floating gate-to-floating gate (fg-fg) interference in flash memory cell read operations |
US10475510B2 (en) * | 2017-12-21 | 2019-11-12 | Macronix International Co., Ltd. | Leakage compensation read method for memory device |
EP3743857A4 (en) * | 2018-01-23 | 2021-12-29 | Anaflash Inc. | Neural network circuits having non-volatile synapse arrays |
US10910061B2 (en) | 2018-03-14 | 2021-02-02 | Silicon Storage Technology, Inc. | Method and apparatus for programming analog neural memory in a deep learning artificial neural network |
US10446246B2 (en) * | 2018-03-14 | 2019-10-15 | Silicon Storage Technology, Inc. | Method and apparatus for data refresh for analog non-volatile memory in deep learning neural network |
US10522226B2 (en) * | 2018-05-01 | 2019-12-31 | Silicon Storage Technology, Inc. | Method and apparatus for high voltage generation for analog neural memory in deep learning artificial neural network |
KR102504836B1 (ko) * | 2018-06-15 | 2023-02-28 | 삼성전자 주식회사 | 보상 회로를 구비하는 저항성 메모리 장치 |
US10643119B2 (en) | 2018-07-24 | 2020-05-05 | Sandisk Technologies Llc | Differential non-volatile memory cell for artificial neural network |
CN110189788A (zh) * | 2019-04-24 | 2019-08-30 | 深圳市金泰克半导体有限公司 | 闪存的读电压确定方法、装置、计算机设备和存储介质 |
US20200364583A1 (en) | 2019-05-14 | 2020-11-19 | Robert D. Pedersen | Iot sensor network artificial intelligence warning, control and monitoring systems and methods |
CN209657299U (zh) | 2019-05-16 | 2019-11-19 | 北京知存科技有限公司 | 模拟向量-矩阵乘法运算电路以及芯片 |
US11507816B2 (en) * | 2019-09-19 | 2022-11-22 | Silicon Storage Technology, Inc. | Precision tuning for the programming of analog neural memory in a deep learning artificial neural network |
-
2020
- 2020-03-25 US US16/829,757 patent/US11636322B2/en active Active
- 2020-03-26 US US16/830,733 patent/US20210209457A1/en active Pending
- 2020-07-02 CN CN202080091622.3A patent/CN114930458A/zh active Pending
- 2020-07-02 EP EP20746800.0A patent/EP4085461B1/en active Active
- 2020-07-02 WO PCT/US2020/040755 patent/WO2021137894A1/en unknown
- 2020-07-02 JP JP2022540417A patent/JP7404542B2/ja active Active
- 2020-07-02 KR KR1020227020817A patent/KR20220104004A/ko not_active Application Discontinuation
- 2020-09-03 WO PCT/US2020/049235 patent/WO2021137900A1/en unknown
- 2020-09-03 EP EP20775481.3A patent/EP4085464A1/en not_active Withdrawn
- 2020-09-03 JP JP2022540418A patent/JP7329151B2/ja active Active
- 2020-09-03 KR KR1020227020818A patent/KR20220104005A/ko not_active Application Discontinuation
- 2020-09-03 CN CN202080091624.2A patent/CN114902339A/zh active Pending
- 2020-12-14 TW TW109143997A patent/TWI785435B/zh active
- 2020-12-14 TW TW111140771A patent/TWI799355B/zh active
- 2020-12-14 TW TW109143998A patent/TWI815065B/zh active
-
2022
- 2022-07-27 US US17/875,281 patent/US11847556B2/en active Active
-
2023
- 2023-12-13 JP JP2023209950A patent/JP2024028955A/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030128567A1 (en) | 2002-01-07 | 2003-07-10 | Chih-Kang Chiu | Sensing apparatus for a ROM memory device |
JP2006114078A (ja) | 2004-10-12 | 2006-04-27 | Toshiba Corp | 不揮発性半導体記憶装置及びその動作方法 |
US20110122684A1 (en) | 2009-11-20 | 2011-05-26 | Industrial Technology Research Institute | Voltage compensation circuit, multi-level memory device with the same, and voltage compensation method for reading the multi-level memory device |
Also Published As
Publication number | Publication date |
---|---|
TW202309789A (zh) | 2023-03-01 |
TW202129552A (zh) | 2021-08-01 |
JP2024028955A (ja) | 2024-03-05 |
EP4085461A1 (en) | 2022-11-09 |
KR20220104004A (ko) | 2022-07-25 |
US11636322B2 (en) | 2023-04-25 |
TWI785435B (zh) | 2022-12-01 |
JP2023509636A (ja) | 2023-03-09 |
TWI799355B (zh) | 2023-04-11 |
JP7404542B2 (ja) | 2023-12-25 |
US20220374699A1 (en) | 2022-11-24 |
WO2021137900A1 (en) | 2021-07-08 |
EP4085461B1 (en) | 2024-04-10 |
US20210209457A1 (en) | 2021-07-08 |
KR20220104005A (ko) | 2022-07-25 |
US20210209456A1 (en) | 2021-07-08 |
CN114930458A (zh) | 2022-08-19 |
JP2023509635A (ja) | 2023-03-09 |
CN114902339A (zh) | 2022-08-12 |
EP4085464A1 (en) | 2022-11-09 |
WO2021137894A1 (en) | 2021-07-08 |
US11847556B2 (en) | 2023-12-19 |
TWI815065B (zh) | 2023-09-11 |
TW202134910A (zh) | 2021-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7329151B2 (ja) | 人工ニューラルネットワーク内のアナログニューラルメモリにおけるデータドリフトを補償するための回路 | |
JP2023515531A (ja) | 深層学習人工ニューラルネットワークにおけるアナログニューラルメモリセルの超精密チューニング | |
JP7201831B2 (ja) | 深層学習人工ニューラルネットワークにおけるアナログニューラルメモリ用の精密プログラミング回路 | |
JP2022549112A (ja) | 深層学習人工ニューラルネットワークにおけるアナログニューラルメモリのプログラミングのための精密な調整 | |
JP2023525771A (ja) | 論理セル及び改善されたプログラミング機構を備える人工ニューラルネットワーク内のアナログニューラルメモリアレイ | |
TWI809663B (zh) | 用於人工神經網路中之類比神經記憶體之精確資料調校方法及裝置 | |
KR20230110360A (ko) | 딥 러닝 인공 신경망에서의 아날로그 신경 메모리를위한 디지털 출력 메케니즘 | |
JP2023533719A (ja) | 人工ニューラルネットワークにおけるアナログニューラルメモリアレイの適応バイアスデコーダ | |
US20210209458A1 (en) | Precise data tuning method and apparatus for analog neural memory in an artificial neural network | |
US20240120009A1 (en) | Programming of a Selected Non-volatile Memory Cell by Changing Programming Pulse Characteristics | |
TWI843232B (zh) | 決定施加至神經網路中的一或多個記憶體胞元的偏壓 | |
TWI842636B (zh) | 深度學習人工神經網路中類比神經記憶體的輸出電路 | |
US20240062813A1 (en) | Determination of a bias voltage to apply to one or more memory cells in a neural network | |
US20230154528A1 (en) | Determination of a bias voltage to apply to one or more memory cells in a neural network | |
WO2024063792A1 (en) | Verification method and system in artificial neural network array | |
CN118043889A (zh) | 要施加到神经网络中的一个或多个存储器单元的偏置电压的确定 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20220825 |
|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20220825 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20230725 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20230804 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 7329151 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |