Artificial Intelligence

The maximum amount of text (measured in tokens) that a language model can process in a single input-output cycle. The context window determines how much prior conversation or document content the mode...

A class of deep neural networks most commonly applied to visual imagery analysis. CNNs use convolutional layers that apply learnable filters to detect features like edges, textures, and shapes, buildi...

A statistical technique for evaluating machine learning models by partitioning data into subsets, training on some subsets and validating on others. K-fold cross-validation rotates the validation set...

A set of techniques used to artificially increase the size and diversity of training datasets by creating modified versions of existing data. Common methods include image rotation, flipping, cropping,...

The process of assigning meaningful tags or annotations to raw data such as text, images, or audio to create training datasets for supervised learning. Data labeling quality directly impacts model acc...

A subset of machine learning that uses artificial neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data. Deep learning excels at tasks like image re...

Synthetic media created using deep learning techniques, typically involving the replacement of a person's likeness in images or videos with someone else's. Deepfakes raise significant concerns about m...

A class of generative models that learn to create data by reversing a gradual noising process. Diffusion models progressively add noise to data during training and learn to denoise it during generatio...

Techniques that reduce the number of input features in a dataset while preserving as much relevant information as possible. Methods like PCA, t-SNE, and UMAP help visualize high-dimensional data, redu...

A regularization technique in neural networks where randomly selected neurons are temporarily removed during training. Dropout prevents co-adaptation of neurons and reduces overfitting by forcing the...

The deployment of AI algorithms and models directly on edge devices such as smartphones, IoT sensors, and embedded systems, rather than relying on cloud-based processing. Edge AI enables real-time inf...

A dense vector representation of data (text, images, or other objects) in a continuous vector space where similar items are positioned closer together. Embeddings capture semantic relationships and ar...

A machine learning approach that combines multiple models to produce better predictions than any individual model. Techniques include bagging (Random Forest), boosting (XGBoost, AdaBoost), and stackin...

One complete pass through the entire training dataset during model training. Multiple epochs are typically needed for a model to converge, but too many epochs can lead to overfitting. The optimal numb...

AI systems and techniques designed to make their decision-making processes transparent and understandable to humans. XAI aims to provide clear explanations of how and why a model produces its outputs,...

The process of selecting, transforming, and creating input variables (features) from raw data to improve machine learning model performance. Feature engineering requires domain knowledge and can signi...

A machine learning approach where a model is trained across multiple decentralized devices or servers holding local data, without exchanging the data itself. Only model updates are shared, preserving...

A machine learning approach where a model learns to perform a task from only a small number of examples. In the context of LLMs, few-shot learning involves providing a few demonstration examples withi...

The process of taking a pre-trained model and training it further on a smaller, task-specific dataset to adapt it to a particular use case. Fine-tuning adjusts the model's weights to specialize its kn...

A large AI model pre-trained on broad, diverse data at scale that can be adapted to a wide range of downstream tasks. Foundation models like GPT-4, Claude, Gemini, and Llama serve as general-purpose b...