Latest Updates from Tech world

Friday 22 December 2017

How does bitcoin works?

Bitcoin:What is it?How does it work?How to use it?What is meant by a cryptocurrency?What is block chain?What is bitcoin mining?

How does bitcoin works
The Bitcoin is attracting global attention due to it's recent surge in value and growing acceptance as a form of payment with more and more merchants, retailers and individuals.To understand what is bit coin really is and how it works,a little technical knowledge is required.In this article we have tried to answer a few questions arise in your mind about bitcoin and it's working in simple words.

What is bitcoin?

Bitcoin is a digital cryptocurrency believed to be developed by a pseudonym entity Known as Satoshi Nakamoto.It is It is just one among thousands of cryptocurrencies. But it is widely accepted as the first successful and most popular cryptocurrency on web.

Bitcoin is a software developed based on the blockchain protocoal.It appeared on the internet in January 2009.

Blockchain:Block chain is distributed ledger that can record record financial transactions.It is a continuously growing list of records, called blocks, which are linked and secured using cryptography. Each block typically contains a hash pointer(an address) as a link to a previous block,a timestamp and transaction data.

A blockchain is typically managed by a peer-to-peer network collectively adhering to a protocol for validating new blocks. Once recorded, the data in any given block cannot be altered retroactively without the alteration of all subsequent blocks, which requires involvement of the network majority.So,a blockchain cannot be corrupted easily unless majority users want to bring down the network.

How blockchain works?

Here is the sequence of changes occurs in a blockchain network during a transaction is performed


The blockchain database isn’t stored in any single location, meaning the records it keeps are truly public and easily verifiable. No centralized version of this information exists for a hacker to corrupt. Hosted by millions of computers simultaneously, its data is accessible to anyone on the internet. Since each block is linked to previous block via hash pointer data corruption becomes nearly impossible.To corrupt a block it's subsequent block also need to be edited.

Blockchain originally devised for the digital currency, Bitcoin,but the tech community is now finding other potential uses for the technology.

Blockchain is a list of verified transactions. For example,A sent X bitcoin to B on December 14, 2017, between 12:10 p.m and 12:20 p.m.Bitcoin's blockchain is public. Anyone can download it.
Bitcoin transaction data available on blockchain.info website

We have seen there is no central authority to verify transactions and maintain ledger.Then who will do this verification and ledger maintains? Are they paid for this?

Usually in a currency system central bank is responsible for the issue of currency.Here who will issue bitcoin?

Mining

The process of issuing new bitcoin into the circulation is called mining. Miners will verify transaction and add validated transaction to the ledger. As a reward of their work new coins will be issued and given to them.

At first it seems to be simple.But real process involved in mining is difficult.Bitcoin's software makes the process artificially time consuming.If mining process is made simple bitcoin will be worthless. Think about Gold.Why it so much valuable?Because , it is rare and limited and process involved in mining and purification is expensive

It's not just one transaction individuals are trying to verify. All the transactions are gathered into blocks with a virtual lock on them.A miner has to verify a block of 1MB of data. By verifying transactions, miners are helping to prevent the "double-spending problem." If no one is verifying any transactions fraudsters may have the chance to spend the same coin again and again.

After transaction verification you will get some task to complete. One who complete this task is the winner of subsequent bitcoins issued.To earn something "proof of work" is required.

Miners receives the latest block of transaction data. They run the data through a cryptographic algorithm that generates a "hash," a string of numbers and letters that serves to verify the information's validity, but does not reveal the information itself.
Actually there is no advanced math or computation is involved in this 'math problem'.What miners doing is trying to be the first one to come up with a 64-digit hexadecimal number (a "hash") that is less than or equal to the target hash. It's basically guess work.

To generate maximum number of hashes you need high power computing devices.Powers of such computers are expressed in MegaHash per second(MH/s) or GigaHash per second(MH/s)
Answer to the said math problem is a 64-digit hexadecimal number. Then, you can image how difficult is to guess that number.

Miners don't generate 64 bit hex number, instead they generate 'nouces' ( "number only used once," )and the nonce is the key to generating these 64-bit hexadecimal numbers In Bitcoin mining, a nonce is 32 bits in size--much smaller than the hash, which is 256 bits(64*4). The first miner whose nonce generates a hash that is less than or equal to the target hash is awarded credit for completing that block, and is awarded the newly issued bitcoin.

Here you can see the details of the block number 350010 and it's corresponding hash,nounces,reward etc..
block hash and nounces in bitcoin
All target hashes begin with zeros--at least eight zeros, and up to 63 zeros.

There is no minimum target, but there is a maximum target set by the Bitcoin Protocol. No target can be greater than this number:
00000000ffff0000000000000000000000000000000000000000000000000000

You may have doubt in mind that is it so much difficult to guess a hexa decimal number. You can check the current difficulty level of guessing a nounce that produce a hash less than or equal to a target hash from the block explorer site. When I am writing this it has reached {"difficulty":1873105475221.611}. That means chance of win for a nounce is 1/ 1873105475221.611.

Let us analyze this situation with some smaller number.

Suppose target hash is between 1 and 100.Three persons were asked to guess the target number.They need not guess exact number ,instead number less than or equal to the target. First person guesses 25, second person 27 and third person 67.But the target was 45. Then Who is the winner. First and second guessed a number less than 45 which satisfies the condition for a win. In bitcoin scenario , there cannot be two winner. So, person who have verified block with maximum number of transactions will the winner.

You may be thinking if you choose the smallest number ,you could be the winner all the time. This is not possible in bitcoin mining algorithm.'Nounce' once used cannot be reused.Nounces are the key to the hashes. Hash function used in bitcoin is SHA-256 Cryptographic Hash Algorithm.To understand bitcoin completely ,you must know SHA-256 algorithm We will be discussing deeply about SHA-256 algorithm and bitcoin in our coming article.

Friday 15 December 2017

NASA uses Artificial intelligence to finds solar system with earth like planet

NASA with the help of Google's Artificial finds a solar system like ours by analyzing data provided by Kepler Space Telescope
NASA uses google AI to spot exoplanets in kepler 90 solar system
Google's Artificial Intelligence and Neural Network algorithm helped NASA to spot exoplanets in Kepler-90 solar system which is similar to our solar system with 8 planets revolving a star.Credits: NASA
NASA's Kepler Space Telescope launched with a mission to spot earth-like planets outside solar system (exoplanets).So far Researchers have used the NASA Kepler Telescope to discover more than 3,000 different exoplanets.

Recently researchers from NASA announced they have achieved some thing new. Using Google's Artificial Intelligence(AI) and data collected by Kepler Telescope scientists have identified a solar system like ours far far away, containing a star and 8 planets revolving it.

The newly-discovered Kepler-90i – a sizzling hot, rocky planet that orbits its star once every 14.4 days.About 30 percent larger than Earth, Kepler-90i is so close to its star that its average surface temperature is believed to exceed 800 degrees Fahrenheit, on par with Mercury. Its outermost planet, Kepler-90h, orbits at a similar distance to its star as Earth does to the Sun.“The Kepler-90 star system is like a mini version of our solar system. You have small planets inside and big planets outside, but everything is scrunched in much closer,” said Vanderburg, a NASA Sagan Postdoctoral Fellow and astronomer at the University of Texas at Austin.

Why Artificial Intelligence?

NASA's Kepler Telescope has been searching alien worlds since 2009.Kepler’s dataset consists of more than 35,000 possible planetary signals. Automated tests, and sometimes human eyes, are used to verify the most promising signals in the data. However, the weakest signals often are missed using these methods.NASA was waiting for the right tool or technology to unearth them.Here comes the tech giant Google's Artificial Intelligence and Neural Network.
Read More about Artificial Intelligence and Neural Networks

How researchers used Gooogle's Artificial Intelligent Neural Network to search earth like planets and solar systems like our's?

Shallue, a senior software engineer with Google’s research team Google AI, came up with the idea to apply a neural network to Kepler data. He became interested in exoplanet discovery after learning that astronomy, like other branches of science, is rapidly being inundated with data as the technology for data collection from space advances.

“In my spare time, I started googling for ‘finding exoplanets with large data sets’ and found out about the Kepler mission and the huge data set available,” said Shallue. "Machine learning really shines in situations where there is so much data that humans can't search it for themselves.”

NASA's Website says,'The discovery came about after Christopher Shallue along with another reasearcher Andrew Vanderburg trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler – the minuscule change in brightness captured when a planet passed in front of, or transited, a star. Inspired by the way neurons connect in the human brain, this artificial “neural network” sifted through Kepler data and found weak transit signals from a previously-missed eighth planet orbiting Kepler-90, in the constellation Draco.'

How Neural Network is trained to identify exoplanets?

A neural network is like our brain. If it is taught with enough examples , it can take decisions thereafter.So, researchers trained the neural network to identify transiting exoplanets using a set of 15,000 previously identified exoplanet data.The network learned it and identified similar data patterns in the huge collection of Kepler data.

In the test set, the neural network identified correct set of exoplanet data with 96% accuracy.After number of testings the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets. Their assumption was that multiple-planet systems would be the best places to look for more exoplanets.

Neural network will become more precise as it is fed with more and more data patterns. Shallue and Vanderburg plan to apply their neural network to Kepler’s full set of more than 150,000 stars so that more exoplanets can be sifted out.

Read More on NASA Website

Thursday 14 December 2017

Origin of Bitcoin and mystery surrounding it

How Bitcoin originated and who created it?

how and who created bitcoin and mystery behind bitcoin

Bitcoin originated in 2009.Since then Bitcoin has experienced significant highs and lows. Last week, the cryptocurrency surpassed an $16,000 evaluation for the first time in history. Bitcoin is considered the preeminent cryptocurrency in the world. There's plenty of mystery surrounding its creation.Who created it ,how it is created etc..

Here is the timeline of Bitcoin,
In 2008, the first inklings of bitcoin begin to circulate the web. In August 2008, the domain name bitcoin.org was registered online. Two months later, a paper entitled 'Bitcoin: A Peer-to-Peer Electronic Cash System' authored by ‘Satoshi Nakamoto’.But who is this Satoshi Nakamoto.Identity of Satoshi Nakamoto is still unknown.It may be a single genius or a group of talents who like to stay anonymous for number of reasons.

Bitcoin runs through an autonomous software program.Bitcoin is just one among thousands of cryptocurrency.

In 2010, a handful of merchants started accepting bitcoin in lieu of established currencies.
The cryptocurrency began attracting interest from tech elites, as well. In 2012, Cameron and Tyler Winklevoss purchased $10 million worth of bitcoin, and, in less than a year their investment had more than tripled. It's been estimated the Winklevoss twins own 1% of all available bitcoin.

In 2011, the Silk Road, an online marketplace for illegal drugs, launches. It uses bitcoin as its chief form of currency.

Two years after its origin, the mysterious figure known as "Satoshi Nakamoto" disappears from the web.

Google "Satoshi Nakamoto" and the results will lead you straight to image after image of an elderly Asian man. This is Dorian S. Nakamoto, named "Satoshi Nakamoto" at birth. He is almost 70 years old, lives in Los Angeles with his mother, and, as he has reminded people hundreds of times, is not the creator of Bitcoin.

The Craig Wright controversy:In 2016, Australian entrepreneur Craig Wright claimed to be the creator of Bitcoin and provided disputed code as proof. But finally he also withdrew.

In the course of determining the identity of Satoshi Nakamoto, there's one person who has been thumbed again and again: hyper-secretive cryptocurrency expert Nick Szabo, who was not only fundamental to the development of Bitcoin, but also created his own cryptocurrency called "bit gold" in the late '90s.

In 2014, a team of linguistic researchers studied Nakamoto's writings alongside those of thirteen potential bitcoin creators. The results, they said, were indisputable. “The number of linguistic similarities between Szabo’s writing and the Bitcoin whitepaper is uncanny," the researchers reported, "none of the other possible authors were anywhere near as good of a match."Szabo firmly denied these claims, both in The New York times story and in a tweet: "Not Satoshi, but thank you."

Recently , Tesla and SpaceX founder Elon Musk denied being Bitcoin's creator. 

Nakamoto has written extensively about Bitcoin, authoring close to 80,000 words on the subject in the course of two years. His work reads like that of a native English speaker. Judging by Nakamoto’s spelling, and his use of British colloquialisms, it's thought he might hail from the UK. The timing of his posts seem to indicate this fact as well: It's been pointed out that Nakamoto posted during UK daylight hours.

The Wikipedia entry on Satoshi Nakamoto names at least 13 potential candidates as being responsible for the creation of Bitcoin.

Why would the inventor of the world's number one cryptocurrency choose to remain anonymous?It might have number of reasons.

History of such currencies are not quite good.

In 1998, Hawaiian resident Bernard von NotHaus dabbled in a fledgling form of currency called "Liberty Dollars" to disastrous results: He was charged with violating federal law and sentenced to six months of house arrest, along with a three-year probation.

In 2007, one of the first digital currencies, E-Gold, was shut down amid contentious circumstances by the government on grounds of money laundering.

If the inventor of Bitcoin wants to remain anonymous, it's for good reason: by maintaining anonymity, they've avoided adverse legal consequences, making their anonymity at least partially responsible for the currency's success.

Besides, one of the founding principals of Bitcoin is that it's a decentralized currency, untethered to conspicuous institutions or individuals. In his original proposition on Bitcoin, Nakamoto wrote, "What is needed is an electronic payment system based on cryptographic proof instead of trust, allowing any two willing parties to transact directly with each other without the need for a trusted third party."

A closer look at one of Nakamoto's original postings on the proposal of Bitcoin sheds some light on his possible motivations.

In February 2009, Nakamoto wrote, "The root problem with conventional currency is all the trust that's required to make it work. The central bank must be trusted not to debase the currency, but the history of fiat currencies is full of breaches of that trust. Banks must be trusted to hold our money and transfer it electronically, but they lend it out in waves of credit bubbles with barely a fraction in reserve. We have to trust them with our privacy, trust them not to let identity thieves drain our accounts."

Even after 9 years of its creation , brain behind bitcoin is still a mystery.

Read Bit coin original Whitepaper: https://bitcoin.org/bitcoin.pdf

Saturday 9 December 2017

Flexible Mobile Phone displays: Rumours and realities

Flexible,foldable,rollable displays:When it will hit the market?Reality check and rumours.

LG flexible display
LG flexible display

Content Highlights
  • First bendable e-paper (Gyricon)
  • Samsung bendable smartphone
  • Samsung Galaxy X  rumors 
  • LG flexible display
  • Apple's patent application for flexible display concept
  • Lenovo bendable phone CPlus
  • ITRI and BOE flexible display prototypes

Every smartphone lover is waiting for a smartphone that can be folded or rolled like paper.Let us have check at how long we have to wait for such a product.

First Flexible Display

Flexible electronic paper (e-paper) based displays were the first flexible displays conceptualized and prototyped. This form of flexible displays has a long history.Many companies attempted but failed to design slated for mass production that can be used in consumer electronics. One of the notable among such prototypes was Gyricon put forth by Xerox PARC. Still mass production of e-paper  is expensive.
Gyricon flexible e-paper
flexible e-paper

How Gyricon e-paper works?

Gyricon contains a lots of small spherical beads, sandwiched in between two thin transparent plastic sheet.The beads, each contained in an oil-filled cavity, are free to rotate within those cavities. The beads are "bichromal", with hemispheres of two contrasting colours (e.g. black and white, red and white).  Each side of the bead has  electrical charge (positive or negative), so they exhibit an electrical dipole. When voltage is applied to the surface of the sheet, the beads rotate to present one coloured side to the viewer. Voltages can be applied to the surface to create images such as text and picture.
Cross section of Gyricon flexible e-paper
Gyricon cross section
 They remain fixed in position until another electrical charge is applied to change the orientation of the beads. So, there is no need of power after text/picture is written.This e-paper can be erased and rewrite infinite time(theoretically) by applying corresponding voltages.

Current trends in flexible and foldable displays 

Recently  flexible display market has gained great momentum owing to the competition and usage in various areas likes mobile phones, laptops and other handheld consumer electronic devices. Due to the advent of advanced materials and new technologies, display market is evolving at higher speed.

OLED based flexible displays have gained more attention than any other flexible display technology. Many leading companies have displayed their version of flexible displays in recent times. Apart from prototypes commercial production is yet to begin. Even though there  are many challenges and hurdles  in incorporating  flexible displays in consumer electronics,tech giants  like LG, Samsung, Sharp and Sony are in the brim of it. Commercial release of such display based electronic devices are expected in the last quarter of 2018.

News from tech world hits at commercial release of flexible display devices sooner. Let us have look at where tech companies stand in flexible display technology.

CES 2013: Samsung flexible phone prototype unveiled

Samsung unveiled its flexible phone prototype, running Windows Phone 8 and branded Youm, during a keynote at CES .On stage at the Consumer Electronics Show in Las Vegas, the prototype phone was shown being flexed and bent without any conspicuous colour distortion, with other pre-recorded demonstrations shown on film.
Samsung has been working on flexible displays for a number of years, but its latest demonstration was the first to prove it has already talked to other companies about how it might implement flexible displays.

Samsung brings the foldup phone a step closer with the world's first 'stretchable' display

Recently Samsung has unveiled a radical 9.1-inch stretchable display .A flexible OLED (organic light-emitting diode) screen which could stretch in both direction by as much as 12 millimetres might spell out a new era in phone screen technology, the report says.
Samsung says the stretchy screen will be useful for everything from wearables to in-car displays, and could also lead to a new generation of wearable devices that can be knocked or dropped and simply move back into place.
Samsung flexible and stretchable display
samsung stretchable display
Samsung stretchable flexible display
samsung stretchable display
When the screen is pressed from above, the screen is dented like a rubber balloon, then returns to its original flat shape.The Korean manufacturer revealed the panel at the Society for Information Display 2017 event in the LA Convention Centre..

Samsung Galaxy X: Rumors and news leaks

Samsung has long been rumored to be prepping the Galaxy X for a release sometime in 2017.
Samsung will “test the waters” with the limited run prototype, which may launch in 2018.
The phone is described as having two OLED display panels with a hinge in the middle. Screens without bezels, like the ones used on the Galaxy S8, may be used to create a seamless, one-screen look.
Samsung foldable  flexible display patent application
Samsung flexible display patent application

A patent application reveals a number of renders and illustrates the smartphone’s hinge from a number of angles. Check out the latest photos below.

 Apple seeks new patent for folding displays 

 apple flexible display patent application
The US Patent & Trademark Office has published an Apple patent application for a foldable display. This follows earlier rumors that the company was working with LG on a future foldable iPhone.
‘An electronic device may have a flexible portion that allows the device to be folded. The device may have a flexible display. The flexible display may have a bending region that allows the display to bend along a bend axis when the device is folded’.Patent describes.

The patent describes a display that can be ‘opened and closed like a book’ .Display may include an array of display pixels formed from liquid crystal display (LCD) components, an array of electrophoretic display pixels, an array of organic light-emitting diode display pixels, an array of pixels formed from crystalline semiconductor light-emitting diode dies (sometimes referred to as micro-LEDs), an array of electrowetting display pixels, or display pixels based on other display technologies.
apple flexible iphone concept

LG’s  unveiled its latest OLED screen which is  transparent and flexible

On June 22 2017 LG announced that it’s created the world’s first flexible, transparent 77-inch OLED display.  display is 77 inches on the diagonal with an aspect ratio of 16:9.The screen has a UHD resolution of 3840 x 2160, offers up to 40 percent transparency, and can be fixed with a curvature of up to 80 degrees.
LG flexible display
LG 77 inch bendable display
 On LG’s official website, it is see that company’s goal is to start mass production of FHD Curved OLED and Wide area flexible display by end of 2017.

Currently based on the information available LG is the front runner in flexible display technology. Partnership between Apple and LG in display production  proves above statement to be true.

Apart from above tech giant,s few Chinese entities like ITRI and BOE have invested in flexible display field.

Lenovo Bendable phone 

In 2016, Lenovo unveiled working prototypes of bendable smartphones and tablets. The project was codenamed CPlus. You can wear it around your wrist like a smartwatch.No official release date was announced yet.
Lenovo CPlus phone display

ITRI demonstrates a foldable AMOLED prototype

ITRI flexible display prototype
ITRI flexible display prototype
ITRI is a nonprofit R&D organization engaging in applied research and technical services in Taiwan.
ITRI institute demonstrated a new foldable AMOLED display prototype, saying that its technology is rapidly approaching "commercial standards". It’s developers claims “ITRI has developed a transparent OLED display based on its FlexUP™ substrate. With the advantages of being flexible and transparent, this technology could be utilized in automotive display, e.g. on windshield glass and side windows. This transparent OLED display offers enhanced user experience in the automotive display and thus opens an opportunity for the next generation display. Watch videoRead more about ITRI flexible display

BOE Display's latest flexible and foldable AMOLED display prototypes

BOE flexible display
BOE flexible display
Chinese firm BOE Display(BOE Technology Group Co., Ltd.) demonstrated its first batch of flexible OLED panels made at its new B7 6-Gen OLED fab in Chengdu.  . The production line is the world’s second production line for flexible AMOLED panels and China’s first. The line is expected to break the monopoly enjoyed by Korean companies  Samsung, LG and others. Already, there are indications that Huawei, Xiaomi, OPPO, Vivo and other OEMs are showing interests in patronizing the BOE AMOLED display.  Watch video BOE flexible display 

Conclusion: After going through the latest developments and news and considering the fact that technology is evolving faster than ever, it is obvious that by the end of 2018 foldable and smartphones will hit the market. Already LG has rolled out curved/flexible display panels suitable for TVs, but incorporating flexible displays with handheld devices pose no of challenges. For mass production price also need to be contained. In coming years more researches, investments  and innovations are expected in this field.

Wednesday 22 November 2017

What is artificial neural network and how it works?

What is a neural network?How it works and how it is can be the key element of Artificial Intelligence and Machine learning?

Artificial neural network is inspired by biological nervous system.
An Artificial Neural Network (ANN) is an information processing system that is inspired by the biological nervous systems. Artificial Neural network is an attempt to mimics animal brain. Neural network consist of large number of highly interconnected processing elements (neurones) working in unison to solve complex problems. Whether it is biological or artificial neural network neurons are the building blocks. The concept of Artificial Intelligence and neural networks established before the advent of computers, but many important advances have been boosted by the use of computer emulations.
Artificial intelligence and neural networks already applied in information processing systems, pattern recognition, medical diagnosis etc. Still there is a long way to go. This field offers infinite opportunity in coming decades.

Biological neurons V/S artificial neurons

Human brain is composed of billions of neurons and other specialised cells. Brain is the least explored and most complex organ of our body. We know only less than 1% of our brain. But we have a vague idea about learning mechanism of our brain.


Structure of biological neuron


A neuron receives signals from other neurons through a host of fine structures called dendrites. The neuron sends out spikes of electrical signals through a long, thin stand known as an axon, which splits into thousands of branches. At the end of each branch, a structure called a synapse converts the activity from the axon into electrical effects that inhibit or excite activity in the connected neurons. When a neuron receives excitatory input that is sufficiently large compared with its inhibitory input, it sends a spike of electrical activity down its axon. Learning occurs by changing the effectiveness of the synapses so that the influence of one neuron on another changes. In other words information is stored in these junctions between each neurons.

Biological to artificial neurons

Now let us see how an artificial neuron model is designed to mimic the basic functions of a neuron. An artificial neuron is a device with many inputs and one output. Dendrites will be replaced by input, processing unit will function as cell body and axon will be replaced by output line. We can program/ teach cellbody/processing unit to get desired output.

A simple neuron

The neuron has two modes of operation; the training mode and the using mode. In the training mode, the neuron can be trained to produce a particular output, for a set of inputs. In the using mode, when a taught input pattern is detected at the input, its associated output becomes the current output. If the input pattern does not belong in the taught list of input patterns, the firing(excitation) rule is used to determine the output state.

Artificial neural network example

For example, a 3-input neuron is taught to output 1 when the input (X1,X2 and X3) is 111 or 101 and to output 0 when the input is 000 or 001. Then, the truth table is;

X1:
0
0
0
0
1
1
1
1
X2:
0
0
1
1
0
0
1
1
X3:
0
1
0
1
0
1
0
1
OUT:
0
0
?
?
?
1
?
1

Output for the inputs 010,011,100 and 110 is not known to neuron. Here comes the firing rule Take the pattern 010. It differs from 000 in 1 element, from 001 in 2 elements, from 101 in 3 elements and from 111 in 2 elements. Therefore, the 'nearest' pattern is 000 which belongs in the 0-taught set. Thus the firing rule requires that the neuron should not fire when the input is 001. On the other hand, 011 is equally distant from two taught patterns that have different outputs and thus the output stays undefined (0/1).

By applying the firing in every column the following truth table is obtained;

X1:
0
0
0
0
1
1
1
1
X2:
0
0
1
1
0
0
1
1
X3:
0
1
0
1
0
1
0
1
OUT:
0
0
0
?
?
1
1
1

Therefore the firing rule enables neuron to respond 'sensibly' to patterns not seen during training.
More complicated neuron architecture

Above neuron doesn't do anything that conventional computers don't do already.In a neural network output of one neuron is given as input to another neuron. So, more sophisticated and meaningful neuron can be designed obtained by giving weight to each input. The effect that each input has at decision making is dependent on the weight of the particular input. The weight of an input is a number which when multiplied with the input gives the weighted input. These weighted inputs are then added together and if they exceed a pre-set threshold value, the neuron fires. In any other case the neuron does not fire.

Output=f(X1W1+X2W2+………..+XnWn)
This neuron has the ability to adapt to a particular situation(inputs) by changing its weights and/or threshold.

We have seen in biological neurons ‘Learning occurs by changing the effectiveness of the synapses so that the influence of one neuron on another changes’

In artificial neurons learning occurs by changing its weights on particular input, thus changing the effect of one neuron on another. Various algorithms exist that cause the neuron to 'adapt'.

Neural network



A neural network is an interconnection of large number of neurons. Output of one neuron will be fed to input of one or more neurons. Apart from the input and output layers , hidden layers are include so that output will be fine tuned and error free. As the number of neurons in a network increases, intelligence of that network will also improve(as in biological neural system).

Neuron:An example

In above figure neuron is trained to recognise the patterns X and Y. The associated patterns are all black and all white respectively as shown below.Let us assume input is captured by 3 X 3 sensor array
.
If we represent black squares with 1 and white squares with 0 then the truth tables for the neuron is.
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
0
1
0
1
0
1
0
1
X
The truth table for above pattern is as follows.
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
0
1
1
1
1
0
1
0
Y
Above two input sets are the taught input sets. Now, let us see what will be the output of the neuron if another set of input is introduced.
Truth table for the above pattern is given below. Initially output of the above pattern unknown to the neuron, but, on application of firing rule neuron will conclude above pattern is similar to taught input corresponds to ‘X’.
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
1
1
0
1
0
1
1
1
X
Neuron will look for the similarity of this input with the taught inputs. This truth table is similar to first truth table in 7 ways(7 inputs are similar) and to the second table in 4 ways only. So, neuron will give the output as ‘X’.
By applying firing rule neuron will conclude above pattern is ‘Y’ since it’s 5 input are similar to taught inputs of ‘Y’ and only 3 inputs are similar to taught inputs of ‘X’.
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
0
1
0
1
0
0
1
0
Y
Similarly observing other patterns given below you can see that , with only two taught input sets , system can identify up to five set of inputs. If a single neuron can do this much, what would be the capability of a network of tens, thousands or millions of neurons.? Today this algorithm can be implemented using simple computer programs.
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
0
1
0
1
0
1
1
1
X
A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
1
1
0
1
0
1
0
1
X

A1
A2
A3
A4
A5
A6
A7
A8
A9
o/p
1
0
1
1
1
1
0
0
1
Y
Artificial neural network application

  • Neural networks are best in pattern identification, identifying particular trends in a set of data, they are well suited for prediction or forecasting needs in sales, marketing, customer research, planning etc..
  • Medicine: Artificial neural nets are capable of disease diagnosis and treatment suggestions. Neural networks learn by example so the details of how to recognise the disease are not needed. What is needed is a set of examples that are representative of all the variations of the disease. Their problem solving ability and precision improves after each task(like humans).
  • Humanoid Robots: Artificial intelligence can be incorporated into robotic brains using neural networks.
  • Software :Pattern Recognition in facial recognition, optical character recognition, etc.
  • Self driving vehicles and autopiloting
Many applications of Neural Networks are yet to be explored. Their ability to learn by example makes them very flexible and powerful. With the advancement of high power computing we have a lot to gain from neural networks.Scientists believe that some day a 'consious' networks might be produced.For that neural network will be the biggest contributor along with other technologies.

Join Our Newsletter