In a neural network, a bias is a learned number added to a neuron's weighted sum before the activation function. It shifts the neuron's output up or down, letting the network fit patterns that do not pass through zero.
A weight is a learned number in a neural network that controls how strongly one input or neuron influences the next. Training is the process of adjusting millions or billions of weights so the network's predictions become accurate.
A hidden layer is any layer of neurons between a neural network's input and output layers. Hidden layers transform the input into increasingly useful internal features, and stacking many of them is what makes a network deep.
An activation function is a mathematical function applied to a neuron's weighted sum that decides its output. It adds non-linearity, which lets neural networks learn complex patterns instead of only straight-line relationships.
A recurrent neural network (RNN) is a type of neural network designed for sequences such as text, speech and time series. It processes one step at a time and carries a hidden state, a kind of short-term memory, from each step to the next.
A convolutional neural network (CNN) is a type of deep learning model designed for grid-like data such as images. It slides small learned filters across the input to detect patterns like edges, textures and shapes, then combines them to recognise objects.
An artificial neuron is the basic building block of a neural network. It takes several numeric inputs, multiplies each by a learned weight, adds a bias, and passes the total through an activation function to produce a single output.
An ML pipeline is an automated sequence of steps that takes raw data through preparation, training, evaluation and deployment to a monitored machine learning model, making the process repeatable and reliable.
A loss function is a formula that measures how far a machine learning model's predictions are from the correct answers. Training works by adjusting the model to make this number as small as possible.
Gradient descent is an optimisation algorithm that trains machine learning models by repeatedly adjusting their parameters in the direction that most reduces the error, like walking downhill step by step to reach the lowest point.
Model variance measures how much a machine learning model's predictions would change if it were trained on a different sample of data. High variance means the model is overly sensitive to its training data and tends to overfit.
In machine learning, model bias usually means error caused by a model's overly simple assumptions, which makes it miss real patterns. The term is also used for unfair outcomes against certain groups, which is a separate but important problem.
Underfitting happens when a machine learning model is too simple or poorly trained to capture the real pattern in the data, so it performs badly on both training data and new data.
Overfitting happens when a machine learning model learns its training data too closely, including random noise, so it performs very well on training data but poorly on new, unseen data.
A test dataset is a portion of data kept completely separate from training and tuning, used once at the end to give an honest estimate of how a machine learning model will perform on new, real-world data.