AIWiki
Malaysia

Search Results

15 results for NPU

Infrastructure

AI Guardrails

AI guardrails are runtime safety mechanisms that validate, filter, and enforce policies on large language model inputs and outputs in production systems, preventing harmful content, data leakage, prompt injection, and off-topic behaviour.

6 min readUpdated June 2026
Infrastructure

AI PC

A personal computer equipped with a dedicated Neural Processing Unit (NPU) designed to accelerate on-device artificial intelligence workloads locally, without requiring cloud connectivity, for tasks such as image generation, speech recognition, and language model inference.

7 min readUpdated June 2026
Foundations

Attention Mechanism

A neural network technique that enables models to dynamically weight the relevance of different parts of an input sequence when producing each output element, forming the core of transformer architectures.

6 min readUpdated May 2026
Foundations

Autoencoder

An autoencoder is a type of artificial neural network trained to reconstruct its input through a compressed internal representation, used for dimensionality reduction, feature learning, and anomaly detection.

5 min readUpdated May 2026
Foundations

Encoder-Decoder Architecture

A neural network design pattern that compresses an input sequence into an internal representation using an encoder, and then generates an output sequence from that representation using a decoder, foundational to machine translation, summarisation, and many other sequence-to-sequence tasks.

6 min readUpdated May 2026
Models

GPT-4

GPT-4 is a large multimodal language model developed by OpenAI, released in March 2023, that accepts both image and text inputs and demonstrates human-level performance on numerous professional and academic benchmarks.

6 min readUpdated May 2026
Foundations

Hallucination (AI)

A phenomenon in which an artificial intelligence system generates output that is factually incorrect, fabricated, or unsupported by its input, while presenting it with apparent confidence.

6 min readUpdated May 2026
Applications

In-Context Learning

In-context learning is the ability of large language models to perform new tasks by conditioning on examples or instructions provided within the input prompt, without updating model weights.

5 min readUpdated June 2026
Infrastructure

Inference (Machine Learning)

Inference is the phase in which a trained machine learning model is used to generate predictions or outputs from new input data, distinct from the earlier training phase.

5 min readUpdated May 2026
Foundations

Mixture of Experts

Mixture of Experts (MoE) is a machine learning architecture in which a model routes each input to a small subset of specialised sub-networks called experts, enabling large model capacity at a fraction of the compute cost.

6 min readUpdated June 2026
Applications

Prompt Engineering

The practice of designing and optimising input instructions given to large language models to elicit accurate, relevant, and well-structured outputs for a given task or application.

7 min readUpdated May 2026
Infrastructure

Prompt Injection

Prompt injection is a security vulnerability affecting large language model applications in which an attacker embeds adversarial instructions in model inputs to override the system's intended behaviour, bypass safety controls, or exfiltrate sensitive information.

7 min readUpdated June 2026
Foundations

Sequence-to-Sequence Model

A neural network architecture composed of an encoder that processes an input sequence into a fixed representation and a decoder that generates an output sequence from that representation, forming the foundation for machine translation, summarisation, and dialogue systems.

7 min readUpdated June 2026
Foundations

Token

A token is the smallest unit of text processed by a large language model, typically representing a word, subword, or character used as the fundamental input and output element during inference.

6 min readUpdated June 2026
Foundations

Tokenisation

Tokenisation is the process of breaking text into discrete units called tokens — which may represent words, subwords, characters, or symbols — that serve as the fundamental input units for language models and other natural language processing systems.

6 min readUpdated May 2026