Artificial Neural Network (NNs)
Artificial Neural Network (ANNs) is also known as Neural Network (NNs) or quasi-neural network. In the field of machine learning and cognitive science, it is a mathematical model or computational model that imitates the structure and function of biological neural networks (the central nervous system of animals, especially the brain).A neural network is a large number of artificial neurons connected together to perform computations. It uses interconnected nodes, or neurons, in a hierarchical structure similar to the human brain. It can create adaptive systems that computers use to learn from their mistakes and continually improve. Thus, artificial neural networks can attempt to solve complex problems, such as summarizing documents more accurately or recognizing faces.
Importance of Neural Networks
Neural networks can help computers make intelligent decisions with limited human assistance because they can learn and model nonlinear and complex relationships between input and output data.
Neural networks can understand unstructured data and make general observations without explicit training. For example, they can broadly recognize that Baxter Road is a place name, while Baxter Smith is a person name. They can also recognize that two different input sentences have similar meanings:
- Could you tell me how to pay?
- How do I transfer funds?
The neural network will know that these two sentences mean the same thing.
Types of Neural Networks
Types of neural networks can be categorized by how data flows from input nodes to output nodes. Here are some examples:
Feedforward Neural Network
Feedforward neural networks process data in a unidirectional manner from input nodes to output nodes, with each node in one layer connected to every node in the next layer. Feedforward networks use a feedback process to improve predictions over time.
Back Propagation Algorithm
Artificial neural networks use corrective feedback loops to continuously learn to improve their predictive analysis. In simple terms, you can think of data flowing from input nodes to output nodes through many different paths in a neural network. But there is only one path that maps the input node to the correct output node. To find this path, the neural network uses feedback loops, which work like this:
- Each node makes a guess about the next node in the path.
- It checks whether the guess is correct or not. The node will assign higher weight values to paths that lead to more correct guesses and lower weight values to node paths that lead to incorrect guesses.
- For the next data point, the node makes a new prediction using the higher-weighted path and repeats step 1.
Convolutional Neural Networks
The hidden layers in a convolutional neural network perform specific mathematical functions (such as summarization or filtering) called convolutions. They are very useful for image classification because they can extract relevant features from the image that are useful for image recognition and classification. This new form is easier to process without losing features that are critical to making good predictions. Each hidden layer extracts and processes different image features, such as edges, color, and depth.
References
【2】https://aws.amazon.com/cn/what-is/neural-network/?nc1=h_ls