A Post-Quantum Associative Memory

Lami, Ludovico; Goldwater, Daniel; Adesso, Gerardo

doi:10.48550/arxiv.2201.12305

Cited by 6 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiment is inspired by the work of Lami, Goldwater and Adesso [17], who proposed a post-quantum associative memory using GPT. The results of our experiment indicate that the ChatGPT model has a high level of creative potential, generating insightful and thought-provoking outputs that encourage further exploration of the field.…”

Section: Discussionmentioning

confidence: 99%

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Adesso

2023

Preprint

View full text Add to dashboard Cite

This paper presents a novel approach to scientific discovery using an artificial intelligence (AI) environment known as ChatGPT, developed by OpenAI. This is the first paper entirely generated with outputs from ChatGPT. We demonstrate how ChatGPT can be instructed through a gamification environment to define and benchmark hypothetical physical theories. Through this environment, ChatGPT successfully simulates the creation of a new improved model, called GPT , which combines the concepts of GPT in AI (generative pretrained transformer) and GPT in physics (generalized probabilistic theory). We show that GPT can use its built-in mathematical and statistical capabilities to simulate and analyze physical laws and phenomena. As a demonstration of its language capabilities, GPT also generates a limerick about itself. Overall, our results demonstrate the promising potential for human-AI collaboration in scientific discovery, as well as the importance of designing systems that effectively integrate AI’s capabilities with human intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Adesso

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Our experiment is inspired by the work of Lami, Goldwater and Adesso (Lami et al, 2021), who proposed a post-quantum associative memory using GPT. In addition to its impressive performance on the evaluation criteria, GPT 4 is also able to exhibit self-awareness, allowing it to understand and analyze its own structure and behavior.…”

Section: Discussionmentioning

confidence: 99%

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Adesso

2022

Preprint

View full text Add to dashboard Cite

We introduce a powerful general probabilistic theory, GPT$^4$, that extends classical and quantum theories to include higher-dimensional probabilistic models. GPT$^4$ results from the four-fold integration of GPT in physics (General Probabilistic Theory) and GPT in AI (Generative Pretrained Transformer). In this paper, which is entirely generated by GPT$^4$, we demonstrate the capabilities of GPT$^4$ by using it to construct a new model of the universe that includes all known physical laws and phenomena. We show that GPT$^4$ can use its built-in mathematical and statistical capabilities to simulate and analyze the behavior of the universe, making predictions and testing the validity of different physical theories. As a demonstration of its language capabilities, GPT$^4$ also generates a limerick about itself. GPT$^4$ estimates that AI will have a probability of over 95% to surpass humanity within approximately 5 years. Our results show that GPT$^4$ provides a self-aware description of the physical world, making it a useful tool for understanding and analyzing the universe.

show abstract

“…Generalised contextuality has also recently been connected to the framework of generalised probabilistic theories [58,59,60,61] (see also [62] for an application to associative memories). This framework is commonly used in foundations research and allows one to transform any probabilistic theory, such as classical and quantum theory, into a simple linear structure in which the states and effects are represented as vectors in a vector space 10 .…”

Section: Possible Extensions To Our Frameworkmentioning

confidence: 99%

Contextuality and inductive bias in quantum machine learning

Bowles¹,

Wright²,

Farkas³

et al. 2023

Preprint

View full text Add to dashboard Cite

Generalisation in machine learning often relies on the ability to encode structures present in data into an inductive bias of the model class. To understand the power of quantum machine learning, it is therefore crucial to identify the types of data structures that lend themselves naturally to quantum models. In this work we look to quantum contextuality-a form of nonclassicality with links to computational advantage-for answers to this question. We introduce a framework for studying contextuality in machine learning, which leads us to a definition of what it means for a learning model to be contextual. From this, we connect a central concept of contextuality, called operational equivalence, to the ability of a model to encode a linearly conserved quantity in its label space. A consequence of this connection is that contextuality is tied to expressivity: contextual model classes that encode the inductive bias are generally more expressive than their noncontextual counterparts. To demonstrate this, we construct an explicit toy learning problem-based on learning the payoff behaviour of a zero-sum game-for which this is the case. By leveraging tools from geometric quantum machine learning, we then describe how to construct quantum learning models with the associated inductive bias, and show through our toy problem that they outperform their corresponding classical surrogate models. This suggests that understanding learning problems of this form may lead to useful insights about the power of quantum machine learning.

show abstract

A Post-Quantum Associative Memory

Cited by 6 publications

References 42 publications

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI

Contextuality and inductive bias in quantum machine learning

Contact Info

Product

Resources

About