A subset of machine learning focused on neural networks with many layers, enabling complex data representation.

A computational model inspired by the human brain, consisting of interconnected nodes (neurons) to process data.

A specialized neural network architecture designed for processing structured grid data, such as images.

The ability of a system to identify and classify objects within digital images using deep learning.

Techniques used to artificially expand training datasets by applying transformations to existing data.

The process of optimizing the parameters that govern the training process of a machine learning model.

The process of integrating a trained machine learning model into a production environment for real-world use.

A mathematical function applied to a neural network's output to introduce non-linearity into the model.

A modeling error that occurs when a model learns noise in the training data instead of the actual data distribution.

A scenario where a model is too simple to capture the underlying patterns in the data, resulting in poor performance.

A technique where a pre-trained model is fine-tuned on a new task, leveraging existing knowledge.

A technique to improve training speed and stability by normalizing the output of a previous activation layer.

A function that measures the difference between the predicted output and the actual output during model training.

An algorithm used to adjust the weights of a neural network to minimize the loss function.

A subset of data used to train a machine learning model, allowing it to learn patterns.

A subset of data used to tune the model's hyperparameters and prevent overfitting.

A separate subset of data used to evaluate the performance of a trained model.

One complete pass through the entire training dataset during the training process.

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

Different layers in a CNN, such as convolutional layers, pooling layers, and fully connected layers, each serving specific functions.

The capability of a model to make predictions on new data instantly as it is received.

An architectural style for designing networked applications, allowing interaction with web services.

Quantitative measures used to assess the effectiveness of a machine learning model, such as accuracy and F1 score.

An interdisciplinary field that enables computers to interpret and process visual information from the world.

A software library that provides tools and functions to facilitate the development of machine learning models.