Neuromorphic computing aims to mimic the human brain's architecture for efficient processing in various applications such as healthcare, drones, and autonomous systems. This technology utilizes components like memristors and is designed to enhance energy efficiency and computation power, reducing reliance on traditional processing systems. Existing neuromorphic research chips from companies like IBM and Intel demonstrate its potential in realizing these advanced computational tasks.

1. NEUROMORPHIC COMPUTING
-By N.C.CHANDU PRASANTH
N C CHANDU PRASANTH YOUTUBE CHANNEL
1

2. Contents
1
•Introduction
2
• Architecture& Building Blocks
3
•Applications
4
• Existing Neuromorphic Research Chips
N C CHANDU PRASANTH YOUTUBE CHANNEL
2

3. Introduction
Neuromorphic Computing refers to computing structures and algorithms that
were inspired by the biological nervous system, and currently it is used in a
wide variety of applications which are difficult to explicitly program.
Some examples include recognition tasks, decision making, and forecasting.
Neuromorphic Computing is a concept developed by Caver Mead in late
1980’s
In neuromorphic computing, you basically take inspiration from the
principles of the brain and try to mimic those on hardware utilising
knowledge from nanoelectronics and VLSI
Neuromorphic architectures needed to: produce lower energy consumption,
potential novel nanostructured materials, and enhanced computation.
N C CHANDU PRASANTH YOUTUBE CHANNEL
3

4. These kind of chips are already present in some products
as well. If you look at Apple’s latest iPhone, they have a
chip called M1, which is an AI processor. This is not
something that is far off into the future.
N C CHANDU PRASANTH YOUTUBE CHANNEL
4

5. Why Neuromorphic Computing??
CPU Needs More Memory Compared to GPU
Speed of CPU less when Compared to GPU
N C CHANDU PRASANTH YOUTUBE CHANNEL
5

6. Efficient Processing Engine- Brain
N C CHANDU PRASANTH YOUTUBE CHANNEL
6

7. Proposed Architecture
N C CHANDU PRASANTH YOUTUBE CHANNEL
7

8. Conventional Circuits Vs Neuromorphic Circuits
N C CHANDU PRASANTH YOUTUBE CHANNEL
8

9. Different Parts of Neuron
 Dendrites: tree-like projections arising from the body of the neuron,
 Soma: The cell body contains genetic information, maintains the neuron's
structure, and provides energy to drive activities.
 Axon/ Nerve Fibre: carries nerve impulses away from the cell body.
 Synapses: refer to the points of contact between neurons where information
is passed from one neuron to the next.
N C CHANDU PRASANTH YOUTUBE CHANNEL
9

10. Building Blocks of Neuromorphic System
 Synapses  Memristor to design electronic circuits, passive elements like
as capacitors, resistors, and inductors are used, but a fourth fundamental
element also exists, which is called a “memristor”
 Memristors are important because they retain memory without power, and
non-volatile.
N C CHANDU PRASANTH YOUTUBE CHANNEL
10

11. Memtransistor & FerroElectric FETS
N C CHANDU PRASANTH YOUTUBE CHANNEL
11

12. Soma These type of devices provide two important functions:
1. Integration
2. Threshold Spiking
A possible implementation of such a device consists of a capacitor
in parallel with a memristor
Axon Long Wire: Assumed to provide a circuit connection and a
time delay line. much more research is needed to understand its role
and how to construct a device that resembles its function
Dendrites: pseudo-3D systems have been implemented in multilayer
(~8) CMOS-based architecture.
N C CHANDU PRASANTH YOUTUBE CHANNEL
12

13. Applications
In the filed of HealthCare:
 You need to get a lot of data from the patients for the development of personalized
medicine, genome sequencing, etc. While the current sensor technology is
efficient in extracting such data, processing it in real time is the bottleneck.
 Neuromorphic computing would enable processing capabilities within the
sensors themselves. Therefore, in the future, we may expect significant
developments in critical fields like personalized medicine, genome sequencing,
etc.,.
N C CHANDU PRASANTH YOUTUBE CHANNEL
13

14. Drones or Warfare Systems
Their camera captures good quality images but extracting information
from the images in real time is the bottleneck. Drones are connected to
Wi-Fi and send images to the base station. The base station processes the
data and sends the signals back. This is a power-hungry process and can
be intercepted too. If the drone itself has the capacity to process the
data, it can take immediate action.
N C CHANDU PRASANTH YOUTUBE CHANNEL
14

15. Space Applications
Even in space, rovers capture images and send them back to the earth
station for processing. If an energy-efficient processing system is
installed there, we’ll have Mars rovers and Moon rovers driving on
their own
N C CHANDU PRASANTH YOUTUBE CHANNEL
15

16. Other Applications
 Also, we use all sorts of applications like Alexa, Siri, etc, but they do not work
without Wi-Fi. The main problem with these systems is that their processing
power is limited. Whenever we give them any input, they just transfer it to the
server, where the processing happens. The output comes from the server to the
device, and the device simply gives us the output.
 In such a scenario, we not only make these devices compute independently
but we also reduce the cloud dependence, which is a major source of security
vulnerabilities and adversary attacks.
Autonomous Vehicles
and Robots
N C CHANDU PRASANTH YOUTUBE CHANNEL
16

17. Existing Neuromorphic Research Chips
IBM TrueNorth Chip: Functions like a Brain
IBM research, namely, a biologically inspired chip
(“TrueNorth”) that implements one million spiking neurons
and 256 million synapses on a chip with 5.5 billion
transistors with a typical power draw of 70 milliwatts
N C CHANDU PRASANTH YOUTUBE CHANNEL
17

18. Intel’s Loihi Chip
 a neuromorphic research test chip designed by Intel Labs that uses an
asynchronous spiking neural network (SNN) to implement adaptive self-
modifying event-driven fine-grained parallel computations used to implement
learning and inference with high efficiency. The chip is a 128-neuromorphic
cores many-core IC fabricated on Intel's 14 nm process
N C CHANDU PRASANTH YOUTUBE CHANNEL
18

19. 8-32 Neuromorphic Research Chips
N C CHANDU PRASANTH YOUTUBE CHANNEL
19

20. N C CHANDU PRASANTH YOUTUBE CHANNEL
20