Results for "learning like humans"

How well a model performs on new data drawn from the same (or similar) distribution as training.

Separating data into training (fit), validation (tune), and test (final estimate) to avoid leakage and optimism bias.

A robust evaluation technique that trains/evaluates across multiple splits to estimate performance variability.

Scalar summary of ROC; measures ranking ability, not calibration.

Plots true positive rate vs false positive rate across thresholds; summarizes separability.

A proper scoring rule measuring squared error of predicted probabilities for binary outcomes.

Penalizes confident wrong predictions heavily; standard for classification and language modeling.

Average of squared residuals; common regression objective.

Uses an exponential moving average of gradients to speed convergence and reduce oscillation.

One complete traversal of the training dataset during training.

Halting training when validation performance stops improving to reduce overfitting.

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

Methods to set starting weights to preserve signal/gradient scales across layers.

Randomly zeroing activations during training to reduce co-adaptation and overfitting.

Networks using convolution operations with weight sharing and locality, effective for images and signals.

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

A high-capacity language model trained on massive corpora, exhibiting broad generalization and emergent behaviors.

Fine-tuning on (prompt, response) pairs to align a model with instruction-following behaviors.

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Local surrogate explanation method approximating model behavior near a specific input.

Framework for reasoning about cause-effect relationships beyond correlation, often using structural assumptions and experiments.

Processes and controls for data quality, access, lineage, retention, and compliance across the AI lifecycle.

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Central system to store model versions, metadata, approvals, and deployment state.

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.