Monday 31 August 2015

My understanding of neural networks

From what I have read in this article and from other websites defining neural networks, neural networks are systems that are modelled to be in similar structure to the brain and spinal cord. When neural networks decipher input transmitted through voice (Google Voice using it for this function), it divides the word said into many different sounds until it is as basic as a vowel sound using the first layer of the structure that contains input neurons. Once this sound has been found the other sounds in all the words spoken into Google Voice, it is sent to the second layer where the output shall be sent to the third layer. These neural networks have one very useful feature which is that it learns from the data presented to it. Thus, neural networks have been used to interpret voice input to then perform a command or other function.

Thursday 27 August 2015

Add a reply to the post to explain your understanding of neural networks from the article. You may carry out wider research - make sure you use your own expressions in writing your response.

Add a reply to the post to explain your understanding of neural networks from the article. You may carry out wider research - make sure you use your own expressions in writing your response.
In this article, it specifically talks about the topic of neural networks. A neural network is defined  “a computer system modelled on the human brain and nervous system”. A Neural networks are used to estimate or approximate functions that can depend on a large number of inputs. It works by splitting the recorded speech into smaller segments. This means it can identify the vowel sounds and then it will be able to form a word and from there on it can interpret phrases and sentences. 

Neural Networks

The neural network takes speech and breaks it up into smaller parts. It then identifies the vowel sounds so that it can work out what was said. The words are then put back together to form sentences. After it works out what was said, its next job is to find out the meaning of what was said so it can do its job and help the user.

2. add a reply to the post to explain your understanding of neural networks from the article.

From the article, one can conclude that neural networks, systems inspired by the central nervous system of humans and animals, are a way to create a more accurate voice recognition program. It works by splitting the recorded speech into smaller segments so it may identify the vowel sounds of what is being said. It is then able to form a word, and then to form phrases and sentences. This then results in a highly accurate inference on what has been said into the microphone.

Tuesday 25 August 2015

Question 2: Neural networks

The neural network is a system that uses several principles including gradient based training, fuzzy logic, genetic algorithms and Bayesian methods. Neural network simulates the way the human brain works to allow it to recognize patterns and learn things. The neural network is a computer system that is modelled on the human brain and nervous system.

Friday 31 July 2015

Add a reply to the post to explain your understanding of neural networks from the article. 

A neural network is a computer system which is based on the human brain and nervous system. It can be used to help to cut up speech into little segments while using a voice recognition system, and then it identifies vowel sounds. The speech that comes after can decipher how the vowel sounds come together to form words, which fit together to form sentences.

Sunday 26 July 2015

Voice Recognition Errors

Read this article on Google Voice to find out about how neural networks recognise voice commands.

http://www.gizmodo.com.au/2015/07/google-voice-gets-neural-network-powered-transcription-to-slash-errors/

Once you have read the article,
1. add a comment to share your experience in using a voice recognition system - this could include Siri for iOS users.

2. add a reply to the post to explain your understanding of neural networks from the article. You may carry out wider research - make sure you use your own expressions in writing your response.