Code&Data Insights
[Deep Learning] What is Deep Learning? 본문
[ What is Deep Learning? ]
- deep learning is a subset of machine learning. ( subset of AI )
- a type of ML inspired by the structure of the human brain => 'Artificial Neural Network'
- most efficient way to deal with unstructured data
The difference between ML and DL
- ML : The features should be given
- DL : The features are picked out by the neural network without human intervention
=> cost high, but can handle much higher volume of data to train
[ Neural Networks ]
Neural Networks
- neural network consists of Input Layer | Hidden Layer | Output Layer
- neurons : the core entity of a neural network | where the information processing takes place
How it Works?
1) The weighted sum of the inputs is calculated
2) The bias is added
3) The result is fed to an activation function
4) Specific neuron is activated
1) each pixels which make up for 784 pixels.
2) each pixel is fed as input to each neuron of the first layer
3) neurons of one layer are connected to neurons of the next layer through channels
4) each of these channels is assigned a numerical value known as weight
5) the inputs are multiplied to the corresponding weights and their sum is sent as input to the neuron in the hidden layer
6) each of these neurons is associated with a numerical value called the bias which is then added to the input sum
7) this value is then passed through a threshold function( = activation function )
8) the result of the activation function determine if the particular neuron will get activated or not
9) An activated neuron transmits data to the next layer over the channels
10) In the output layer the neuron with the highest value fires and determines the output
==> the values are basically a probability
** During this training process along with the input our network also has the output fed to it
** The predicted output is compared against the actual output to realize the error in prediction
( the magnitude of the error : how wrong is the prediction )
