Machine Learning

A mathematical function applied to the output of each neuron in a neural network, introducing non-linearity into the model. It determines whether a neuron should be "activated" or not, passing its output to the next layer.

A fundamental algorithm used to train artificial neural networks by efficiently calculating the gradient of the loss function with respect to the network's weights. It propagates the error backward through the network to update parameters.

The number of training examples utilized in one iteration of model training, before the model's internal parameters (weights and biases) are updated. It impacts the training speed and stability.

A central concept in machine learning that describes the conflict between a model's ability to fit the training data (low bias) and its ability to generalize to new data (low variance). Reducing one often increases the other.

A table used to evaluate the performance of a classification model, summarizing the number of correct and incorrect predictions made for each class. It shows true positives, true negatives, false positives, and false negatives.

A non-parametric supervised learning algorithm used for both classification and regression tasks. It builds a model in the form of a tree structure, where internal nodes represent tests on features, branches represent outcomes, and leaf nodes represent class labels or values.

A subfield of machine learning that uses artificial neural networks with multiple layers (deep neural networks) to learn complex patterns from large amounts of data. It's particularly effective for tasks like image recognition, natural language processing, and speech synthesis.

One complete pass through the entire training dataset during the training of a machine learning model. In each epoch, the model sees every training example once and updates its weights.

The process of selecting, transforming, or creating new variables (features) from raw data to improve the performance of a machine learning model. It helps the model better understand the underlying patterns and relationships for more accurate predictions.

Individual measurable properties or characteristics of the phenomenon being observed. In machine learning, features are the input variables used by a model to make predictions or classifications.

An iterative optimization algorithm used to find the minimum of a function, typically the loss function in machine learning. It repeatedly adjusts model parameters in the direction opposite to the gradient of the loss function.

The external configuration settings that the practitioner choose to control the learning process of a machine learning model.

An unsupervised learning algorithm used for clustering, which partitions 'n' observations into 'k' clusters. It iteratively assigns each data point to the cluster whose centroid is closest, then updates the centroids.

A non-parametric, instance-based supervised learning algorithm used for both classification and regression. It classifies a new data point based on the majority class or average value of its 'k' nearest neighbors in the feature space.

The target variable or output associated with a given input example in supervised learning. It's the "answer" the model is trying to predict, such as a category or a numerical value.

A hyperparameter that determines the step size at which an optimization algorithm adjusts the model's weights and biases with respect to the loss gradient. A critical factor in how quickly and effectively a model learns.

A supervised learning algorithm used for predicting a continuous target variable based on one or more independent input features. It models the relationship between variables by fitting a linear equation to the observed data.

A statistical model primarily used for binary classification tasks, predicting the probability of an instance belonging to a particular class. Despite its name, it's a classification algorithm, not a regression one.

A mathematical function that quantifies the discrepancy between a model's predicted output and the true target value. The goal of training is to minimize this function, indicating better model performance.

A subset of Artificial Intelligence that enables systems to learn from data, identify patterns, and make decisions with minimal human intervention. It uses various algorithms to process data and improve performance over time, without explicit programming.

Natural Language Processing (NLP) is a field of AI that focuses on enabling computers to understand, interpret, generate, and interact with human language in both written and spoken forms. It involves tasks like sentiment analysis, machine translation, and text summarization.

A phenomenon where a machine learning model learns the training data too well, including its noise and specific patterns, leading to poor performance on new, unseen data. The model becomes overly complex.

An ensemble learning method for classification and regression that operates by constructing a multitude of decision trees during training. It combines the predictions of individual trees to produce a more accurate and stable prediction.

Techniques used to prevent overfitting by adding a penalty to the loss function for complex models. It discourages overly large weights, making the model simpler and improving its generalization ability.

A type of machine learning where an agent learns to make decisions by performing actions in an environment to maximize a cumulative reward. It learns through trial and error, receiving positive or negative feedback for its actions over time.

An advanced technique in reinforcement learning where human preferences and feedback are used to train a reward model, which then guides the policy optimization of a language model or other agent. It helps align model behavior with human values.

A machine learning approach that utilizes a small amount of labeled data combined with a large amount of unlabeled data during training. It aims to leverage the benefits of both supervised and unsupervised learning.

A type of machine learning where the algorithm learns from a labeled dataset, meaning each input example has a corresponding correct output. The goal is to learn a mapping from inputs to outputs to make predictions on new, unseen data.

A powerful supervised learning algorithm used for classification and regression tasks. It works by finding the optimal hyperplane that best separates data points of different classes in a high-dimensional space.

A completely unseen subset of the data used to evaluate the final performance of a trained machine learning model. It provides an unbiased estimate of how well the model generalizes to new data.

A subset of the entire dataset used to train a machine learning model. The model learns patterns and relationships from this data to adjust its internal parameters (weights and biases).

A phenomenon where a machine learning model is too simple to capture the underlying patterns in the training data, resulting in poor performance on both the training and test sets. It fails to learn the relationships effectively.

Unsupervised learning is a type of machine learning where an algorithm learns from unlabeled data, seeking to find hidden patterns, structures, or relationships within the input without any predefined output targets. Common tasks include clustering, dimensionality reduction, and anomaly detection.

A subset of the data used to tune the model's hyperparameters and provide an unbiased evaluation of a model while tuning model hyperparameters. It helps prevent overfitting to the training data.

Internal parameters of a neural network or linear model that are learned during training. Weights determine the strength of connections between neurons, while biases adjust the activation threshold, allowing models to fit data better.