Machine Learning

A machine learning paradigm where the model can query a user to obtain labels for new data points actively.

Machine Learning

Adversarial training improves model robustness by training on deliberately perturbed inputs that are designed to expose failures under a defined threat model.

Agents

Agent memory is the state an AI agent keeps across steps or sessions, such as scratchpad notes, retrieved facts, user preferences, or task history.

Agents

Agentic AI refers to AI systems that can plan, call tools, maintain task state, and take multi-step actions toward a goal.

Agent security

Agentjacking is an informal term for hijacking an AI agent's tools, context, or execution path so it performs attacker-directed actions.

Safety

AI guardrails are controls that constrain, monitor, or validate model behavior before outputs or tool actions reach users or systems.

Data Augmentation

A technique to artificially increase the size of a training dataset by creating modified copies of existing data.

Data Preparation

Synthetic data created to enhance the diversity and quantity of training datasets.

Training Techniques

An algorithm used for training neural networks by calculating gradients of the loss function.

Deep Learning

A technique to improve training speed and stability in deep neural networks by normalizing the inputs of each layer.

Machine Learning

A learning method where the model is trained on a fixed dataset in one go.

Machine Learning

A method of training machine learning models using a subset of the dataset in each iteration.

Statistics

A statistical method using Bayes' theorem to update the probability of a hypothesis as more evidence becomes available.

AI Ethics

A systematic examination of AI models to identify and mitigate biases.

AI Ethics

Techniques and strategies aimed at reducing bias in AI models and datasets.

Distributed Systems

A decentralized digital ledger technology that securely records transactions across multiple computers.

Blockchain

The ability of different blockchain networks to communicate and share data with each other.

Agents

A computer use agent is an AI agent that can inspect screenshots and control a desktop or browser with mouse and keyboard actions.

Data Processing

The process of labeling data for training machine learning models.

Data Processing

The process of increasing the size and diversity of a training dataset by applying transformations.

Data Processing

The process of obtaining and collecting data from various sources.

Data Management

A structured collection of data used for analysis and training machine learning models.

Data Management

The process of dividing a dataset into training, validation, and test sets.

Machine Learning

A machine learning paradigm where the training data is distributed across multiple devices or nodes.