Search Results
15 results for “NPU”
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.