Learn bits
Science & Tech.
Mahesh

13/03/24 10:34 AM IST

Artificial neural network

In News
  • There are three main ways in which ‘machines’ can be classified depending on the way they learn: supervised learning, unsupervised learning, and reinforcement learning.
  • The way in which information flows inside the machine is governed by artificial neural networks (ANNs), the software that ‘animates’ the hardware.
Artificial Nueral networks
  • An ANN comprises computing units, or nodes, connected together in such a way that the whole network learns the way an animal brain does.
  • The nodes mimic neurons and the connections between nodes mimic synapses. Every ANN has two important components: activation functions and weights.
  • The activation function is an algorithm that runs at a node.
  • Its job is to accept the inputs from other nodes to which it is connected and compute an output. The inputs and outputs are in the form of real numbers.
  • The weight refers to the ‘importance’ an activation function gives to a particular input.
  • For example, say there are different nodes to estimate the fur colour, tail length, and dental profile in a given photo of a cat or a dog.
  • All these nodes provide their outputs as inputs to a node responsible for separating ‘cat’ from ‘dog’. This way, the nodes can be ‘taught’ to adjust their outcomes by adjusting the relative weights they assign to different inputs.
  • A node is the ‘site’ of a mathematical function. Put another way, the ANN is like an algorithm that passes information from one activation function to the next in a specific order.
  • The functions modify the information they receive in different ways.
Types of ANNs
  • Transformers are a specialised type of ANN. They are easy to train in parallel, unlike the ANN architectures that preceded it. This is how, for example, ChatGPT could be trained on the entire web.
  • The ANN is broken up into two parts: the encoder and the decoder. Say an ANN is required to recognise the presence of a cat in a photograph.
  • The encoder accepts the photograph, breaks it up into small pieces (say, 10 x 10 pixels), and encodes the visual information as numerical data (e.g. 0s and 1s). The decoder accepts this data and processes the numbers to reconstruct the information content in the photograph.
  • The transformer architecture, originally developed at Google and released in 2017, is designed to maximise the amount of attention an ANN devotes to different parts of the input data. It has better performance as a result.
  • The advent of transformers revolutionised machines’ ability to translate long, complicated sentences.
GPU
  • The GPU is the physical processor that ‘runs’ the ANN. It was originally developed to render graphics for video games.
  • It was better at this task than other processors at the time because it was designed to run computing tasks in parallel. It has been widely adopted since as the basic computing unit for ANNs for the same feature.
Source- The Hindu

More Related Current Affairs View All

10 Jan

Rural landowners in Delhi want repeal of Sections 33 and 81 of Delhi Land Reforms Act

'Both sections dealing with the use and sale of agricultural land have come under the spotlight ahead of the Delhi Assembly elections.' This can only be done by the Central gove

Read More

10 Jan

Pravasi Bharatiya Diwas

'Prime Minister Narendra Modi inaugurated the 18th edition of the Pravasi Bharatiya Diwas  in Bhubaneswar.' The event is held once every two years to “honour the cont

Read More

10 Jan

Deciphering the Indus script

'Recently, Tamil Nadu Chief Minister M.K. Stalin announced a $1-million prize for experts or organisations in the event of their success in deciphering the scripts of the Indus Val

Read More

India’s First Ai-Driven Magazine Generator

Generate Your Custom Current Affairs Magazine using our AI in just 3 steps