Toward Building Science Discovery Machines
- URL: http://arxiv.org/abs/2103.15551v1
- Date: Wed, 24 Mar 2021 14:04:03 GMT
- Title: Toward Building Science Discovery Machines
- Authors: Abdullah Khalili and Abdelhamid Bouchachia
- Abstract summary: We focus on the scientific discovery process where a high level of reasoning and remarkable problem-solving ability are required.
We provide examples of the use of these principles in different fields such as physics, mathematics, and biology.
We argue that in order to build science discovery machines and speed up the scientific discovery process, we should build theoretical and computational frameworks.
- Score: 3.7565501074323224
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The dream of building machines that can do science has inspired scientists
for decades. Remarkable advances have been made recently; however, we are still
far from achieving this goal. In this paper, we focus on the scientific
discovery process where a high level of reasoning and remarkable
problem-solving ability are required. We review different machine learning
techniques used in scientific discovery with their limitations. We survey and
discuss the main principles driving the scientific discovery process. These
principles are used in different fields and by different scientists to solve
problems and discover new knowledge. We provide many examples of the use of
these principles in different fields such as physics, mathematics, and biology.
We also review AI systems that attempt to implement some of these principles.
We argue that in order to build science discovery machines and speed up the
scientific discovery process, we should build theoretical and computational
frameworks that encapsulate these principles. Building machines that fully
incorporate these principles in an automated way might open the doors for many
advancements.
Related papers
- A Review of Neuroscience-Inspired Machine Learning [58.72729525961739]
Bio-plausible credit assignment is compatible with practically any learning condition and is energy-efficient.
In this paper, we survey several vital algorithms that model bio-plausible rules of credit assignment in artificial neural networks.
We conclude by discussing the future challenges that will need to be addressed in order to make such algorithms more useful in practical applications.
arXiv Detail & Related papers (2024-02-16T18:05:09Z) - AI for Mathematics: A Cognitive Science Perspective [86.02346372284292]
Mathematics is one of the most powerful conceptual systems developed and used by the human species.
Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems.
arXiv Detail & Related papers (2023-10-19T02:00:31Z) - DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery
through Sophisticated AI System Technologies [116.09762105379241]
DeepSpeed4Science aims to build unique capabilities through AI system technology innovations.
We showcase the early progress we made with DeepSpeed4Science in addressing two of the critical system challenges in structural biology research.
arXiv Detail & Related papers (2023-10-06T22:05:15Z) - Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems [268.585904751315]
New area of research known as AI for science (AI4Science)
Areas aim at understanding the physical world from subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales.
Key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods.
arXiv Detail & Related papers (2023-07-17T12:14:14Z) - Photonic Neural Networks: A Compact Review [0.0]
This research was selected 18 main articles were among the main 30 articles on this subject from 2015 to the 2022 year.
We try to introduce some important and valid parameters in neural networks.
In this manner, we use many mathematic tools in some portions of this article.
arXiv Detail & Related papers (2023-02-16T16:10:02Z) - On scientific understanding with artificial intelligence [2.2911874889696775]
We seek advice from the philosophy of science to understand scientific understanding.
Then we collect dozens of anecdotes from scientists about how they acquired new conceptual understanding with the help of computers.
For each dimension, we explain new avenues to push beyond the status quo.
arXiv Detail & Related papers (2022-04-04T13:45:13Z) - From Kepler to Newton: Explainable AI-based Paradigm for Science
Discovery [16.392568986688595]
We introduce an Explainable AI-based paradigm for science discovery.
To demonstrate the AI-based science discovery process, we show how Kepler's laws of planetary motion and the Newton's law of universal gravitation can be rediscovered by (Explainable) AI.
arXiv Detail & Related papers (2021-11-24T00:45:27Z) - Standard Model Physics and the Digital Quantum Revolution: Thoughts
about the Interface [68.8204255655161]
Advances in isolating, controlling and entangling quantum systems are transforming what was once a curious feature of quantum mechanics into a vehicle for disruptive scientific and technological progress.
From the perspective of three domain science theorists, this article compiles thoughts about the interface on entanglement, complexity, and quantum simulation.
arXiv Detail & Related papers (2021-07-10T06:12:06Z) - Inductive Biases for Deep Learning of Higher-Level Cognition [108.89281493851358]
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles.
This work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing.
The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities.
arXiv Detail & Related papers (2020-11-30T18:29:25Z) - Scientific intuition inspired by machine learning generated hypotheses [2.294014185517203]
We shift the focus on the insights and the knowledge obtained by the machine learning models themselves.
We apply gradient boosting in decision trees to extract human interpretable insights from big data sets from chemistry and physics.
The ability to go beyond numerics opens the door to use machine learning to accelerate the discovery of conceptual understanding.
arXiv Detail & Related papers (2020-10-27T12:12:12Z) - Computer-inspired Quantum Experiments [1.2891210250935146]
In many disciplines, computer-inspired design processes, also known as inverse-design, have augmented the capability of scientists.
We will meet vastly diverse computational approaches based on topological optimization, evolutionary strategies, deep learning, reinforcement learning or automated reasoning.
arXiv Detail & Related papers (2020-02-23T18:59:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.