The process of categorizing and labeling groups of pixels or vectors within an image based on specific features.

A type of deep learning model specifically designed for processing structured grid data like images, using convolutional layers.

A subset of machine learning that uses neural networks with many layers to analyze various factors of data.

An open-source library developed by Google for numerical computation and machine learning, widely used for building deep learning models.

A high-level neural networks API, written in Python, that runs on top of TensorFlow, simplifying model building.

Techniques applied to raw images to enhance their quality and relevance for model training, including normalization and augmentation.

The process of adjusting the values in an image to a common scale, improving model performance and training stability.

Techniques to artificially expand the size of a training dataset by creating modified versions of images.

Settings or configurations that govern the training process of a model, such as learning rate and batch size.

Quantitative measures used to assess the performance of a model, including accuracy, precision, and recall.

A modeling error that occurs when a model learns the training data too well, failing to generalize to new data.

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

The systematic examination of errors made by a model to understand its limitations and improve performance.

A technique where a pre-trained model is fine-tuned on a new, but related, task, saving training time and resources.

The hardware and software requirements necessary for training deep learning models, including GPUs and cloud services.

Images produced by medical imaging techniques, such as X-rays, MRIs, or CT scans, used for diagnosis.

A collection of data used for training and testing machine learning models, often split into training, validation, and test sets.

The task of predicting the category or class of an object based on input data, commonly used in supervised learning.

A neural network with multiple layers between the input and output, allowing it to learn complex patterns.

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

The specific arrangement and types of layers in a convolutional neural network, influencing its learning capability.

Real-world examples used to illustrate the application of concepts, often highlighting successes and challenges in AI.

Considerations regarding the moral aspects of using AI in healthcare, including bias, privacy, and accountability.

Constructive criticism provided by fellow learners to enhance understanding and improve project outcomes.

The culminating assignment that showcases a student's understanding and application of course concepts in a practical context.