Deep Learning and Neural Network Understanding
What exactly are Neural Networks?
Artificial neural networks (ANNs), also known as neural network, are computing systems inspired by the biological neural networks that comprise animal brains. It is a network of neurons that receives input and generates output without the use of pre-programmed rules.
An ANN is made up of node layers, which include an input layer, one or more hidden layers, and an output layer. Each node links to the others and has its own weight and threshold value. If any individual node’s output exceeds the defined threshold value, that node activates and begins relaying data to the next level of the network. Otherwise, no data is sent to the next network layer.
What exactly is Deep Learning?
Deep learning is a subset of a larger class of machine learning approaches that combine artificial neural networks and representation learning. It mimics how humans acquire some sorts of knowledge.
The “Deep” in Deep Learning refers to the usage of numerous neural network layers. The number of node layers in an ANNs network differentiates a perceptron (single neuron) method from a deep learning algorithm (more than 3 hidden layers).
With its structures like convolutional neural networks and recurrent neural networks applied to domains like computer vision, audio recognition, and natural language processing, among others, deep learning has many real-world applications.
Types of Neural Networks
There are several type of neural networks, however I will be focusing on the following:
- Feed-forward Neural Network
- Convolutional Neural Network (CNN)
- Recurrent Neural Network (RNN)
- Long Short-Term Memory (LSTM)