Kelegan | Tech Fluency for an Evolving World

Definition In artificial intelligence, end-to-end learning is an approach that involves training a single model to perform a task from raw input to final output, without requiring intermediate processing or hand-crafted features [1]. In traditional ma…

Definition An expert system is a computer program that leverages artificial intelligence (AI) technologies to replicate the judgment and behavior of a human or an organization that has experience and a good knowledge of a particular field [1]. An expe…

Definition Federated learning is a machine learning (ML) approach that facilitates the training of AI models across a network of decentralized devices or servers. This empowers multiple devices or systems to act as a team to train a shared model witho…

Definition In machine learning, few-shot learning is a concept with the goal of designing models different from traditional models, that needs just a few training examples - usually 1-10, to learn useful information, thus the term 'few-shot'. …

Definition In artificial intelligence, forward chaining, also referred to as forward reasoning is a data-driven reasoning process that applies rules to known facts to generate new facts or reach a conclusion. The process is iterative in nature and con…

Definition In neural networks, forward propagation also known as forward pass, is a process that turns input data to predictions or outputs. In other words, it is the “thinking” phase of a neural network. When fed an input such as an image or text, fo…

Definition A foundation model, also referred to as general-purpose AI (GPAI) is a type of AI capable of a range of general tasks (such as text synthesis, image manipulation and audio generation). Examples include OpenAI’s GPT-3 and GPT-4, foundation m…