🔢Quantization

Reducing the precision of model parameters to lower memory and compute.

🔁Recurrent Neural Network

A neural network with loops that maintains memory of previous inputs.

📉Regression

The task of predicting a continuous numerical value from input features.

⚖️Regularization

Techniques that penalize complexity to prevent overfitting in models.

🎮Reinforcement Learning

Learning through trial and error by maximizing cumulative reward signals.

🎲Restricted Boltzmann Machine

A generative stochastic neural network with visible and hidden units.

🦾Robotics

The design, construction, and operation of intelligent machines.

🪞Self-Attention

An attention mechanism that relates different positions within a single sequence.

🌗Semi-Supervised Learning

Learning that combines a small amount of labeled data with unlabeled data.

🎤Speech Recognition

Transcribing spoken language into written text.

👨‍🏫Supervised Learning

Learning from labeled data to map inputs to known outputs.

🔊Text-to-Speech

Synthesizing spoken audio from written text.

✂️Tokenization

The process of splitting text into smaller units called tokens.

📚Training Data

The dataset used to teach a machine learning model to make predictions.

🔄Transfer Learning

Reusing knowledge from one task to improve performance on another.

🤖Transformer

A neural network architecture based on self-attention mechanisms.

📉Underfitting

When a model is too simple to capture the underlying structure of data.

🔍Unsupervised Learning

Learning from unlabeled data to discover hidden patterns or structures.

🗜️Variational Autoencoder

A generative model that learns a latent representation of input data.

🔤Word Embedding

A dense vector representation of words that captures semantic meaning.

0️⃣Zero-Shot Learning

A model's ability to handle tasks it was not explicitly trained on.