Artificial Intelligence is a branch of computer science that aims to create intelligent machines that can perform tasks that typically require human intelligence.
In essence, artificially intelligent systems can perform tasks commonly associated with human cognitive functions. These tasks might include understanding and interpreting human speech, identifying complex patterns, visual perception, decision-making, and even translating languages.
<aside> <img src="/icons/phone_red.svg" alt="/icons/phone_red.svg" width="40px" /> While AI might sound like something from a science fiction movie, it's actually an integral part of our daily lives. From smartphone voice assistants like Siri and Google Assistant to recommendation systems on Netflix and Amazon, AI has increasingly become embedded in our everyday experiences.
</aside>
AI works by using algorithms and statistical models to analyse vast amounts of data and to learn from it. One of the key technologies used in AI is machine learning, which involves training computers to recognise patterns in data so that they can make decisions or predictions based on that data. This is done by feeding large datasets into an algorithm and allowing the computer to adjust its parameters until it can accurately predict outcomes.
<aside> <img src="/icons/sliders-horizontal_blue.svg" alt="/icons/sliders-horizontal_blue.svg" width="40px" /> Algorithms are sets of rules or instructions that a computer can follow to solve a problem or complete a task.
While some AI systems are programmed to follow a specific set of rules directly, many modern AI systems learn and adapt over time. This involves learning these rules based on the data they're given, which leads us to the various types of learning in AI:
</aside>
https://www.ceralytics.com/3-types-of-machine-learning
Another important technology used in AI is natural language processing, which allows computers to understand and interpret human language. NLP combines computational linguistics (rule-based modeling of human language) with machine learning models. Together, these technologies enable computers to process human language in the form of text or voice data and to 'understand' its full meaning, complete with the speaker or writer's intent and sentiment.
<aside> <img src="/icons/alien-pixel_green.svg" alt="/icons/alien-pixel_green.svg" width="40px" /> This technology is used in chatbots (ChatGPT, Bard, etc.) and virtual assistants (Siri, Google Assistant, etc.) which can understand and respond to human queries in a natural way.
</aside>
AI also makes use of neural network, which is a type of machine learning model inspired by the structure of the human brain. These networks are used to analyse, classify and cluster data, such as images or audio, and can be trained to recognise specific patterns or objects.
Neural networks consist of interconnected layers of nodes, often referred to as neurons, that loosely mimic the neurons in a biological brain. They contain an input layer, one or more hidden layers, and an output layer.
<aside> <img src="/icons/info-alternate_orange.svg" alt="/icons/info-alternate_orange.svg" width="40px" /> Each node, or neuron, connects to another and has an associated weight and threshold. A neural network takes in inputs, which are then processed in hidden layers using weights that are adjusted during training. The model then outputs a prediction. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data is passed along. The more neurons, the more complex patterns the network can recognise, and the more accurate the predictions become.
</aside>