BIO-INSPIRED ANALOG VLSI CIRCUITS AND THEIR INDUSTRIAL APPLICATION

Eric Vittoz CSEM Centre Suisse d'Electronique et de Microtechnique SA CH-2007 NEUCHATEL, Switzerland
n n n n

Biology-inspiration Examples of industrial application Ongoing research Conclusion.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

BIOLOGY AS A SOURCE OF INSPIRATION In the continous fight for survival all along evolution: n life has invented increasingly complex solutions Biology inspired systems: n borrow some of them n adapt to constraints of available technologies Inspiration for VLSI processing circuits: from the brain Different levels: n Representation of signals and information n Strategies n Architectures n Methodology
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

METHODOLOGY
n

Opportunism: Along evolution, life has made, step after step: - best possible use of existing strucures as... - bootstrap for the next level of compexity. Bottom-up approach, can be applied to VLSI: - identify all properties of technologies, devices, circuits - exploit them opportunistically to build more complex systems. Also: - explore potential of a solution in a broader range - search for hidden advantages of apparent drawbacks.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

OPPORTUNISM: POSSIBLE FUNCTIONS OF MOS TRANSISTORS

n n n n n n n n

Switch (only function used in digital). Voltage-controlled conductance. Voltage-controlled current source. Multiplier (I D ~ VD x VG + terms). Functions x 2, sqrt(x) (strong inversion: IDsat ~ VG2 + terms). Functions e x, ln(x) (weak inversion: I Dsat ~ eVG/nUT ).

Current memory (open or floating gate). Bipolar operation: - precise e x, ln(x) - voltage and temperature references. Light sensor: any junction. Can only be exploited in analog circuits.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

PROSPECTS FOR ANALOG IN SIGNAL PROCESSING

n

Point of view of power consumption: analog interfaces digital is more efficient for traditional processing

(also, qualitatively: chip area) Pmin/f [J]

10-9 10-12 10-15 10-18 0

Digital:

An

al

og

analog for perception

Collective processing in massively parallel systems. n Goal: - make a decision - control an action
n

(also, qualitatively: precision, linearity)

60 90 120

30

SNR [dB]

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

TRANSLINEAR CIRCUITS
[Gilbert, 1975] n

With bipolar transistors: Ii VBEi

cw

VBEi

ccw

VBEi

with: Ii =

VBEi Isi e UT

Ii thus: VBEi = UT ln Isi which yields:

cw = clockwise ccw = counter-clockwise

n

Ii ccwISi ccw

Ii cw ISi cw
=

With MOS transistors in weak inversion: i poor precision acceptable for perceptive processing.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

EXAMPLE OF TRANSLINEAR CIRCUITS VECTOR-LENGTH CALCULATION

[Gilbert, 1975]

Current mode, provide: npn bipolar I1

Iout =

Ii
+

p-MOS in weak inversion + +

I1
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

PSEUDO-CONDUCTANCE/RESISTANCE Linear behaviour of transistors with respect to currents [Bult, 1992] n General case (any current level): same gate voltage I I1 I I2 I1 I2 G1 G2 G2 * for currents G1*
n

conductances G i
n

pseudo-conductances G i*~W/L

Special case of weak inversion ("diffusor" [Boahen, 1992]): i different values of gate voltages possible, thus... i control of G i* by gate voltage, or by... i control current IC: G*~ IC IC Thus: any network of linear controlled resistors can be implemented by transistors only.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

ARCHITECTURES
n

Massive parallelism (10 11 neurons in brain) VLSI technologies: towards billion-transistor chips - large arrays (102-106) of... - simple cells (10 - 103 tr.) - low local speed (< 10kHz) - limited local precision thanks to...

Collective computation of all cells on the best solution - dense interconnections(10 2 to 105 synapses/neuron)

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

EXAMPLES OF COLLECTIVE OPERATORS

n

Normalization

[Gilbert, 1984]

Iini Itot
n

Iouti

i current gain same for all cells i adjusts for: I outi = Itot

cell i
[Lazzaro et al., 1988]

Winner-take-all

I0 Iouti Iini cell i

n

i points on largest current: I0 for largest I ini Iouti = 0 for others Iinimax i value of largest current

Consensus achieved by communication through single wire.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

COMMUNICATION
n n n

High connectivity is needed for collective computation but is a... Major obstacle for implementations in 2-dimensional VLSI. Possible (complementary) solutions: i collective computation via single or few wire(s) i communication with nearest neighbours only i hierarchical interconnections (smaller density for larger distance) i analog multiplexing: - standard row/column scanning - asynchronous and event driven - pulse communication.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

COMMUNICATION BY ADDRESS-CODING EVENTS

[Mahowald, 1992]

Common m-wire bus. n Activity of each cell transmitted as... n Frequency of address-coding events:
n

code of address

m wire bus event (set of very short pulses)

Features: - priority of access based on activity - no clock: phase of events is kept. Parallel access of all cells to the bus - with arbitration or... - without arbitration (random collisions)[Mortara, 1992]

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

STRATEGIES
n

Learning from examples (instead of programming) - on-chip learning not very useful in practice but... - learning on computer during design phase resulting synaptic weights dumped on the chip. Adaptation - in time (high-pass) , to eliminate constant information: novelty detector elimination of constant spatial noise of sensors. - to signal level, to cover wide dynamic range 140 dB of external excitation 40 dB of nerve activation very useful for analog VLSI processing

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

RETINA FOR LOCAL ADAPTATION

[Venier, 1997] n n

I0 R(k) k

I0

I0

Schematic for 1-D array Real implementation: i 2-D array i pseudo-conductances R*,G*

F. G(k) Iout(k) pixel k-1 pixel k

(k) (k) pixel k+1

G(k) proportional to (k) (local photocurrent) i 1/R(k) proportional to F. (k) If R(k) = 0 then I out(k) =I 0 : global normalisation If R(k) >0, each I 0 distributed across area A ~ L 2 = 1/(RG) ~ F i thus: local normalisation in adjustable area A.

n n

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

MEASUREMENTS ON LOCALLY ADAPTIVE RETINA

n n n

Experimental 35x35 hexagonal array of pixels. Output communication by address-coding events. Checker-board illuminated by light gradient:
0

intensity dB

44dB -20

16dB

input current

-40

10

output current n Dynamic range reduced to that of the object contrast.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

20 column

30

REPRESENTATION OF SIGNALS AND INFORMATION

n

Pulse representation (in biology: spikes of action potential) - for communication - for processing (audition...ubiquitous?) time-domain processing degree of coincidence of events synchronization of processes

"Place coding" (patterns of activity in 2D maps)

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

PLACE CODING [Landolt, 1998] Representation of a variable x: set of nodes with preferred values x i i xi particular value x = i (activation grade of node i) i 1 center of gravity 0 x0 x1 x2 x3 x4 x5 x6 x7 x8 x

Computation of z = f(x, y) by network of links: each link is a fuzzy AND gate x Advantages: continuous amplitudes high tolerance to perturbations low power in current mode systematic implementation of any function.
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

Biology-Inspired Analog VLSI:

EXAMPLES OF INDUSTRIAL APPLICATIONS

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

DETECTION OF MAXIMUM SPOT INTENSITY

[Chevroulet et al., 1995]

Control of LCD protection screen Array of 26x26 pixels - light sensor - element of max.-current copier 18V generator, control and test 4x4.5 mm2 in 2m process Reacts in 50s with 1mW.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

CALCULATION OF 1-DIMENSIONAL MOMENTS I0 Ia x=0 resistive I1 R1 R2 Ij IN Rj Rj+1 RN-1 RN Ib x=1 Mxn = Ib 0* Ia VR pseudo-resistive
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

n n

If: R j = jn-1 R1 Then, n th order moment of current distribution:

I0 I2 R1* R2*

Ij Rj*

IN RN*

0* Ib

Center of gravity x 0: i n = 1 (Rj constant) Ib i x0 = Mx/M0 = I + I a b

MONITORING OF SOLAR ILLUMINATION

[Venier et al., 1996] n

Ambiance-control in vehicles - presence of sun - sun intensity - sun azimuth and elevation Array of 1365 pixels - organized in polar coordinates - light sensor - weighted copies of photocurrents Two linear pseudo-resistive neworks - radial - angular Reacts in 1ms for 100A Precision better than 15.

n n

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

MOTION DETECTOR FOR TRACKBALL

n n n

Inspired from rabbits eye Ball with random pattern of dots Illuminated by periodic flashes

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

MOTION DETECTOR FOR POINTING DEVICE

[Arreguit et al.,1996] n

Calculation of the 2 comp. of translation of a random pattern of dots. n detection of horizontal (and vertical) edges E : x(or y) p x (or y) E E E E E E time t row of sensors E E E E E time t+t E
n n

identification of edges moving during t (between 2 snapshots) Motion during t: x (or y) = p*

n n

number of moving edges E total number of edges

current mode analog processing

array of 75 cells, pitch p =300m n resolution above 800 dpi n graceful degradation for defective cells.
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

OPTICAL CHARACTER RECOGNITION

[Masa et al., 1999]

output
n

Convolutive neural network.

n

abstraction level increases at each step.

1 3 5 7 9

2 4 6 8 0

........

All cells in same sub-layer have n same set of weights with shifted receptive field thus: shift invariant. All cells in same column have same receptive field. Weights learned during design
n

implemented as capacitance ratios

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

THREE-LAYER CONVOLUTIONAL NEURAL NETWORK

[Masa et al., 1999]

n n n n n n

100K capacitors ( 50K weights) 6x7mm 2 in 0.5 m process Power consumption: <4mW Speed: 1000 images/s. Equiv. 10 8 multiply and add/sec. Wide range of - fonts - quality of printing Graceful degradation with defects.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

Biology-Inspired Analog VLSI:

ONGOING RESEARCH

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

FEATURE ENHANCEMENT
[Venier et al., 1997] n n n

Edge enhancement by diffusion in linear network (in retinal layer). Address-coding event communication to... Orientation enhancement by nonlinear unisotropic diffusion: i one cell:
photoreceptors edges enhanced

V+

In

V0o
Iin I0

V60o V120o

Out
vertical 60o

orientation enhanced
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

i preferred orientation electrically adjustable.

OCCULO-MOTOR SYSTEM
pris mg rat ing lens retin s a
vi per sual cep tion

sal ien ma cy p

fina furt l user her or pro ces sin g

ret
sensor tors mo rs enso s

ina

fixe

dw

ide

-an

gle

len

cur

ta ent s r s

te

te upda

Tra cki con ng trol

sac cad con es trol

Retina with narrow-field lens delivers high-resolution visual info. i moving optical front end (rotating prisms) to change gaze angle. with wide-angle watches the whole visual field. n Retina i saliency map (degree of interest of various parts in scene).
n n

Chip n Chip

controls saccadic exploration of interesting parts (targets). centers and tracks selected target in closed loop.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

CHIP FOR SACCADES CONTROL

[Landolt, 1997]

visual field of retina

n
n

R target

rotating prisms n Computes 1,2 =f(R) to center visual field of retina on target. n Exploration time of targets function of their degree of interest n nn
n n

Place-coding + communication by address-coding events.

160000 transistors, 15000 capacitors on 45mm 2 (0.5m process). n Total power consumption at 5V: 5mW.

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

CHIP FOR VISUAL TO MOTOR MAPPING Area: 2mm2

[Landolt, 1997]

r r

target

visual field of retina

2 2

rotating prisms n Incremental control: computes 1,2 = f(1,2, r) needed for r

n

Place coding; activation grade represented by : 0...100nA i current (internal):

i pulse frequency (external): 0...1KHz n Total power consumption at 5V: 30W

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

ANALOG FUZZY CONTROLLER

[Landolt, 1996]

~MIN m input variables Vi11 Vr11 Vi1m Vr1m

bump

n rules Vin1 Vr1n I1 Vinm Vrnm

bump

I0

In
bump (activity of rule n)

bump

current splitters

A1
Vi Vr

4-bit weighting of activities

An 1 output Iout

bump circuit (input membership function)

R* R*

R* 2R*

R* R*

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

FUZZY CONTROLLER CHIP

[Landolt, 1996]

n n n n n n n n

Rule array: Supply voltage: Power cons.: Input full scale: Settling time: Accuracy:

8 by 10 1.8V 850nW 1V 0.5ms 2.6% RMS

CMOS process: 2m Chip core area: 1.2x1.1mm 2

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

Further exploration of existing techniques i identification of new applications Exploration of new aspects: i pulse processing (events in time) i stochastic processing i oscillatory behaviour of arrays of nonlinear cells i ......

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

EXAMPLE OF PULSE (SPIKE) PROCESSING n Extraction of voice pitch (frequency of amplitude modulation)

i Behaviour of chopper cell:

1/f0
pulse

i Experimental results:
160 140 spikes/second 120 100 130 100 50
ii iii i ii
i

free-running (f0)
i i ii i i i i i i iiii i i i ii i iii i i

1/f
refractory TR

effect of input integration silicon cochlea

i iii i i

ii

ii i ii

i i

ii

synchronization f = fM
ii i i

i System architecture [van Schaik, 1998]:

1/fM long TR chopper array coincidence detector array
CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1

output of coincidence array (fM = 130Hz)

i i i i i i ii i i i ii iii i i i i i ii i i i i

short TR

0 1

i i iii i i i iii i iii i i i i i

11

41 21 31 array position

51

low fM

high fM

i Application to voice separation?

Biology-inspired systems based on analog VLSI: n still in infancy n slowly growing Potential already demonstrated by working chips: most of them still exploratory n some have already resulted in innovative products.
n

Very attractive for low-power smart microsystems

n

in particular for low-level vision.

May later compete with digital computation even when power is not limited n for complex perception tasks.
n

CSEM, E. Vittoz/ GE99, Alghero, June 11, 1999 - 1