|
Few-shot Learning (natural Language Processing)
Prompt engineering is the process of structuring or crafting an instruction in order to produce the best possible output from a generative artificial intelligence (AI) model. A ''prompt'' is natural language text describing the task that an AI should perform. A prompt for a text-to-text Large language model, language model can be a query, a command, or a longer statement including context, instructions, and conversation history. Prompt engineering may involve phrasing a query, specifying a style, choice of words and grammar, providing relevant context, or describing a character for the AI to mimic. When communicating with a text-to-image or a text-to-audio model, a typical prompt is a description of a desired output such as "a high-quality photo of an astronaut riding a horse" or "Lo-fi slow BPM electro chill with organic samples". Prompting a text-to-image model may involve adding, removing, or emphasizing words to achieve a desired subject, style, layout, lighting, and aestheti ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Generative Artificial Intelligence
Generative artificial intelligence (Generative AI, GenAI, or GAI) is a subfield of artificial intelligence that uses generative models to produce text, images, videos, or other forms of data. These models Machine learning, learn the underlying patterns and structures of their training data and use them to produce new data based on the input, which often comes in the form of natural language Prompt (natural language), prompts. Generative AI tools have become more common since an "AI boom" in the 2020s. This boom was made possible by improvements in transformer (machine learning model), transformer-based deep learning, deep neural networks, particularly large language models (LLMs). Major tools include chatbots such as ChatGPT, Microsoft Copilot, Copilot, Gemini (chatbot), Gemini, Grok (chatbot), Grok, and DeepSeek (chatbot), DeepSeek; text-to-image models such as Stable Diffusion, Midjourney, and DALL-E; and text-to-video models such as Sora (text-to-video model), Sora and Veo ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Language Model
A language model is a model of the human brain's ability to produce natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation,Andreas, Jacob, Andreas Vlachos, and Stephen Clark (2013)"Semantic parsing as machine translation". Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval. Large language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word ''n''-gram language model. History Noam Chomsky did pioneering work on lan ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Tree Search Algorithm
In computer science, tree traversal (also known as tree search and walking the tree) is a form of graph traversal and refers to the process of visiting (e.g. retrieving, updating, or deleting) each node in a tree data structure, exactly once. Such traversals are classified by the order in which the nodes are visited. The following algorithms are described for a binary tree, but they may be generalized to other trees as well. Types Unlike linked lists, one-dimensional arrays and other linear data structures, which are canonically traversed in linear order, trees may be traversed in multiple ways. They may be traversed in depth-first or breadth-first order. There are three common ways to traverse them in depth-first order: in-order, pre-order and post-order. Beyond these basic traversals, various more complex or hybrid schemes are possible, such as depth-limited searches like iterative deepening depth-first search. The latter, as well as breadth-first search, can also be used t ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Meta-learning (computer Science)
Meta-learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn. Flexibility is important because each learning algorithm is based on a set of assumptions about the data, its inductive bias. This means that it will only learn well if the bias matches the learning problem. A learning algorithm may perform very well in one domain, but not on the next. This poses strong restrictions on the use of machine learning or data mining techniques, since the relationship between the learning problem (often some kind of database) and the effectiveness of differen ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Scientific American
''Scientific American'', informally abbreviated ''SciAm'' or sometimes ''SA'', is an American popular science magazine. Many scientists, including Albert Einstein and Nikola Tesla, have contributed articles to it, with more than 150 Nobel Prize-winners being featured since its inception. In print since 1845, it is the oldest continuously published magazine in the United States. ''Scientific American'' is owned by Springer Nature, which is a subsidiary of Holtzbrinck Publishing Group. History ''Scientific American'' was founded by inventor and publisher Rufus Porter (painter), Rufus Porter in 1845 as a four-page weekly newspaper. The first issue of the large-format New York City newspaper was released on August 28, 1845. Throughout its early years, much emphasis was placed on reports of what was going on at the United States Patent and Trademark Office, U.S. Patent Office. It also reported on a broad range of inventions including perpetual motion machines, an 1860 devi ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Fine-tuning (deep Learning)
In deep learning, fine-tuning is an approach to transfer learning in which the parameters of a pre-trained neural network model are trained on new data. Fine-tuning can be done on the entire neural network, or on only a subset of its layers, in which case the layers that are not being fine-tuned are "frozen" (i.e., not changed during backpropagation). A model may also be augmented with "adapters" that consist of far fewer parameters than the original model, and fine-tuned in a parameter-efficient way by tuning the weights of the adapters and leaving the rest of the model's weights frozen. For some architectures, such as convolutional neural networks, it is common to keep the earlier layers (those closest to the input layer) frozen, as they capture lower-level features, while later layers often discern high-level features that can be more related to the task that the model is trained on. Models that are pre-trained on large, general corpora are usually fine-tuned by reusing their ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Broken Neural Scaling Law
In machine learning, a neural scaling law is an empirical scaling law that describes how neural network performance changes as key factors are scaled up or down. These factors typically include the number of parameters, training dataset size, and training cost. Introduction In general, a deep learning model can be characterized by four parameters: model size, training dataset size, training cost, and the post-training error rate (e.g., the test set error rate). Each of these variables can be defined as a real number, usually written as N, D, C, L (respectively: parameter count, dataset size, computing cost, and loss). A neural scaling law is a theoretical or empirical statistical law between these parameters. There are also other parameters with other scaling laws. Size of the model In most cases, the model's size is simply the number of parameters. However, one complication arises with the use of sparse models, such as mixture-of-expert models. With sparse models, during ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Large Language Model Emergent Abilities
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pretrained transformers (GPTs), which are largely used in generative chatbots such as ChatGPT or Gemini. LLMs can be fine-tuned for specific tasks or guided by prompt engineering. These models acquire predictive power regarding syntax, semantics, and ontologies inherent in human language corpora, but they also inherit inaccuracies and biases present in the data they are trained in. History Before the emergence of transformer-based models in 2017, some language models were considered large relative to the computational and data constraints of their time. In the early 1990s, IBM's statistical models pioneered word alignment techniques for machine translation, laying the groundwork for corpus-based language modeling. A smo ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
OpenAI
OpenAI, Inc. is an American artificial intelligence (AI) organization founded in December 2015 and headquartered in San Francisco, California. It aims to develop "safe and beneficial" artificial general intelligence (AGI), which it defines as "highly autonomous systems that outperform humans at most economically valuable work". As a leading organization in the ongoing AI boom, OpenAI is known for the GPT family of large language models, the DALL-E series of text-to-image models, and a text-to-video model named Sora (text-to-video model), Sora. Its release of ChatGPT in November 2022 has been credited with catalyzing widespread interest in generative AI. The organization has a complex corporate structure. As of April 2025, it is led by the Nonprofit organization, non-profit OpenAI, Inc., Delaware General Corporation Law, registered in Delaware, and has multiple for-profit subsidiaries including OpenAI Holdings, LLC and OpenAI Global, LLC. Microsoft has invested US$13 billion ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
University Of Tokyo
The University of Tokyo (, abbreviated as in Japanese and UTokyo in English) is a public research university in Bunkyō, Tokyo, Japan. Founded in 1877 as the nation's first modern university by the merger of several pre-westernisation era institutions, its direct precursors include the '' Tenmongata'', founded in 1684, and the Shōheizaka Institute. Although established under its current name, the university was renamed in 1886 and was further retitled to distinguish it from other Imperial Universities established later. It served under this name until the official dissolution of the Empire of Japan in 1947, when it reverted to its original name. Today, the university consists of 10 faculties, 15 graduate schools, and 11 affiliated research institutes. As of 2023, it has a total of 13,974 undergraduate students and 14,258 graduate students. The majority of the university's educational and research facilities are concentrated within its three main Tokyo campuses: Hongō, ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Interpretability
In mathematical logic, interpretability is a relation between formal theories that expresses the possibility of interpreting or translating one into the other. Informal definition Assume ''T'' and ''S'' are formal theories. Slightly simplified, ''T'' is said to be ''interpretable'' in ''S'' if and only if the language of ''T'' can be translated into the language of ''S'' in such a way that ''S'' proves the translation of every theorem of ''T''. Of course, there are some natural conditions on admissible translations here, such as the necessity for a translation to preserve the logical structure of formulas. This concept, together with weak interpretability, was introduced by Alfred Tarski in 1953. Three other related concepts are cointerpretability, logical tolerance, and cotolerance, introduced by Giorgi Japaridze in 1992–93. See also * Conservative extension * Interpretation (logic) * Interpretation (model theory) * Interpretability logic References * Japaridze, G., a ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Benchmark (computing)
In computing, a benchmark is the act of running a computer program, a set of programs, or other operations, in order to assess the relative performance of an object, normally by running a number of standard tests and trials against it. The term ''benchmark'' is also commonly utilized for the purposes of elaborately designed benchmarking programs themselves. Benchmarking is usually associated with assessing performance characteristics of computer hardware, for example, the floating point operation performance of a CPU, but there are circumstances when the technique is also applicable to software. Software benchmarks are, for example, run against compilers or database management systems (DBMS). Benchmarks provide a method of comparing the performance of various subsystems across different chip/system architectures. Benchmarking as a part of continuous integration is called Continuous Benchmarking. Purpose As computer architecture advanced, it became more difficult to compa ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
