Buzzword Bingo AI: The most important terms to be able to talk about AI

[suchona.kani.z]

Artificial intelligence (AI) is a multidisciplinary field of computer science that aims to develop machines and software capable of imitating human-like intelligence and learning and problem-solving skills. AI systems use algorithms and data to analyze information, recognize patterns, and make decisions or predictions. This technology has wide-ranging applications, such as natural language processing, image recognition, autonomous vehicles, and personalized recommendations, to name a few.


In this picture you can see the hierarchy of the different methods for artificial intelligence,

ML (machine learning)
Machine learning is a subfield of artificial intelligence that focuses on developing algorithms that enable computers to learn from data and make predictions or decisions. These algorithms use statistical methods to peru consumer email list identify patterns in the data and create models that can be applied to new data.

Example algorithms for this are: decision trees, support vector machines or neural networks.

Neural Networks (NNs)
A neural network is an artificial system based on the structure and functioning of the human brain and designed for machine learning and artificial intelligence. It consists of a large number of interconnected neurons that process and transmit information. Each neuron receives input signals, processes them, and passes an output signal to other neurons. Through the training process, the network adjusts its connections and weights to improve performance on a specific task. After training, the neural network can recognize complex patterns and make predictions or decisions based on new data.


An example of a neuron, source

An artificial neuron is a basic unit in neural networks that processes inputs to produce an output. It consists of several components:

Inputs: The neuron receives input signals from other neurons or external data sources. Each input is associated with a weight that represents the strength of the connection.
Weights: The weights are scaling factors that determine the importance of a particular input for the neuron. They are adjusted during the training process.
Transfer function: In the neuron, the input signals are multiplied by their respective weights and then summed to obtain a weighted sum value.
Bias: A bias is a constant value added to the weighted sum to control the shift of the activation threshold.