Encoder-Decoder

Feedforward Network

फिडफरवार्ड नेटवर्क

A neural network where data flows in one direction from input to output.

Forward Propagation

फरवार्ड प्रोपागेसन

Passing input data through a network layer by layer to produce an output.

Hidden Layer

लुकेको तह

A layer between input and output where a network learns intermediate features.

Mixture of Experts (MoE)

मिक्स्चर अफ एक्स्पर्ट्स

An architecture that routes each input to a few specialized sub-networks for efficiency.

Prediction

भविष्यवाणी / अनुमान

The output a model produces for a given input, such as a label, number, or generated text.

Attention Mechanism

एटेन्सन मेकानिज्म / ध्यान संयन्त्र

A technique that lets a model focus on the most relevant parts of the input.

Autoencoder

अटोइन्कोडर

A network that compresses data into a compact code and reconstructs it, useful for learning features.

Autoregressive

अटोरिग्रेसिभ

Generating output one token at a time, each based on all the tokens produced before it.