DEV Community

Cover image for Comprehensive Machine Learning Terminology Guide
Appy
Appy

Posted on

Comprehensive Machine Learning Terminology Guide

Introduction

Welcome to the Comprehensive Machine Learning Terminology Guide! Whether you're a newcomer to the field of machine learning or an experienced practitioner looking to brush up on your vocabulary, this guide is designed to be your go-to resource for understanding the key terms and concepts that form the foundation of ML.


Fundamental Concepts

Machine Learning (ML): A subset of artificial intelligence that focuses on building systems that can learn from and make decisions based on data.

Artificial Intelligence (AI): The broader field of creating intelligent machines that can simulate human thinking capability and behavior.

Deep Learning: A subset of machine learning based on artificial neural networks with multiple layers.

Dataset: A collection of data used for training and testing machine learning models.

Feature: An individual measurable property or characteristic of a phenomenon being observed.

Label: The target variable that we're trying to predict in supervised learning.

Model: A mathematical representation of a real-world process, learned from data.

Algorithm: A step-by-step procedure or formula for solving a problem.

Training: The process of teaching a model to make predictions or decisions based on data.

Inference: Using a trained model to make predictions on new, unseen data.


Types of Machine Learning

Supervised Learning: Learning from labeled data to predict outcomes for unforeseen data.

Unsupervised Learning: Finding hidden patterns or intrinsic structures in input data without labeled responses.

Semi-Supervised Learning: Learning from a combination of labeled and unlabeled data.

Reinforcement Learning: Learning to make decisions by interacting with an environment.

Transfer Learning: Applying knowledge gained from one task to a related task.


Model Evaluation and Metrics

Accuracy: The proportion of correct predictions among the total number of cases examined.

Precision: The proportion of true positive predictions among all positive predictions.

Recall: The proportion of true positive predictions among all actual positive cases.

F1 Score: The harmonic mean of precision and recall.

ROC Curve: A graphical plot illustrating the diagnostic ability of a binary classifier system.

AUC (Area Under the Curve): A measure of the ability of a classifier to distinguish between classes.

Confusion Matrix: A table used to describe the performance of a classification model.

Cross-Validation: A resampling procedure used to evaluate machine learning models on a limited data sample.

Overfitting: When a model learns the training data too well, including noise and fluctuations.

Underfitting: When a model is too simple to capture the underlying structure of the data.


Neural Networks and Deep Learning

Neuron: The basic unit of a neural network, loosely modeled on the biological neuron.

Activation Function: A function that determines the output of a neuron given an input or set of inputs.

Weights: Parameters within a neural network that determine the strength of the connection between neurons.

Bias: An additional parameter in neural networks used to adjust the output along with the weighted sum of the inputs to the neuron.

Backpropagation: An algorithm for training neural networks by iteratively adjusting the network's weights based on the error in its predictions.

Gradient Descent: An optimization algorithm used to minimize the loss function by iteratively moving in the direction of steepest descent.

Epoch: One complete pass through the entire training dataset.

Batch: A subset of the training data used in one iteration of model training.

Learning Rate: A hyperparameter that controls how much to change the model in response to the estimated error each time the model weights are updated.

Convolutional Neural Network (CNN): A type of neural network commonly used for image recognition and processing.

Recurrent Neural Network (RNN): A type of neural network designed to recognize patterns in sequences of data.

Long Short-Term Memory (LSTM): A type of RNN capable of learning long-term dependencies.

Transformer: A model architecture that relies entirely on an attention mechanism to draw global dependencies between input and output.


Feature Engineering and Selection

Feature Engineering: The process of using domain knowledge to extract features from raw data.

Feature Selection: The process of selecting a subset of relevant features for use in model construction.

Dimensionality Reduction: Techniques for reducing the number of input variables in a dataset.

Principal Component Analysis (PCA): A statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables.


Ensemble Methods

Ensemble Learning: The process of combining multiple models to solve a computational intelligence problem.

Bagging: An ensemble method that uses multiple subsets of the training data to train different models.

Boosting: An ensemble method that combines weak learners to create a strong learner.

Random Forest: An ensemble learning method that constructs a multitude of decision trees.


Natural Language Processing (NLP)

Tokenization: The process of breaking down text into individual words or subwords.

Stemming: The process of reducing inflected words to their word stem or root form.

Lemmatization: The process of grouping together different inflected forms of a word.

Word Embedding: A learned representation for text where words with similar meaning have a similar representation.

Named Entity Recognition (NER): The task of identifying and classifying named entities in text.

Sentiment Analysis: The use of natural language processing to identify and extract subjective information from text.


Reinforcement Learning

Agent: The learner or decision-maker in a reinforcement learning scenario.

Environment: The world in which the agent operates and learns.

State: The current situation or condition of the agent in the environment.

Action: A move or decision made by the agent.

Reward: The feedback from the environment to evaluate the action taken by the agent.

Policy: A strategy used by the agent to determine the next action based on the current state.


Advanced Concepts

Generative Adversarial Network (GAN): A class of machine learning frameworks where two neural networks contest with each other.

Attention Mechanism: A technique that mimics cognitive attention, enhancing the important parts of the input data and diminishing the irrelevant parts.

Transfer Learning: A research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.

Few-Shot Learning: A type of machine learning where a model is trained to recognize new classes from only a few examples.

Explainable AI (XAI): Artificial intelligence systems where the results can be understood by humans.

Federated Learning: A machine learning technique that trains an algorithm across multiple decentralized devices or servers holding local data samples.

AutoML: The process of automating the end-to-end process of applying machine learning to real-world problems.


Conclusion

If you are reading this, thank you so much! I appreciate it a lot ❤️.

Follow me on Twitter appyzdl5 for regular updates, insights, and engaging conversations about ML.

My Github with projects like miniGit and ML algos from scratch: @appyzdl

Top comments (0)