AI-ML-DL for scientific discovery

Last updated Nov 14, 2024 Edit Source

See:

• AI/Deep learning/Neural ODEs
• “AI-based conversational models and search engines” in AI/Generative AI/Foundation models

• The AI revolution in science: applications and new research directions
• The AI revolution in scientific research (The Royal Society, The Alan Turing Institute)
• The AI revolution in science
• The researchers using AI to analyse peer review

• #TALK Using AI to Accelerate Scientific Discovery (Demis Hassabis, Deepmind)

• #CODE Gt4sd-core (IBM) - GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process
  • https://gt4sd.github.io/gt4sd-core/
  • https://research.ibm.com/blog/generative-models-toolkit-for-scientific-discovery
  • https://thenewstack.io/ibms-open-source-gt4sd-generates-ideas-for-scientists/
• #CODE Deep Search
  • https://ds4sd.github.io/
  • https://research.ibm.com/interactive/deep-search/
  • Deep Search extracts and structures data from documents in four steps: Parse, Interpret, Index, and Integrate
  • Handling Scientific Articles with Deep Search
• Consensus - Ask a question, get conclusions from research papers

• NeurIPS - Machine Learning and the Physical Sciences
• Machine Learning and the Physical Sciences, NeurIPS 2024

• #PAPER Artificial intelligence in research (Musib 2017)
• #PAPER Machine learning and the physical sciences (Carleo 2019)
• #PAPER A Survey of Deep Learning for Scientific Discovery (Raghu & Schmidt, 2020) ^dlscience20
• #PAPER DeepXDE: A deep learning library for solving differential equations (Lu 2020)
  • #CODE https://github.com/lululxvi/deepxde
  • https://deepxde.readthedocs.io/en/latest/
• #PAPER SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks (Haghighat 2020)
  • #CODE https://github.com/sciann/sciann
• #PAPER Learning an Accurate Physics Simulator via Adversarial Reinforcement Learning (Jiang 2021)
• #PAPER Machine Learning for Scientific Discovery (Surana 2021)
• #PAPER Machine Intelligence for Scientific Discovery and Engineering Invention (Daniels 2021). White paper
• #PAPER Optimizing the synergy between physics and machine learning (2021). Editorial
• #PAPER Data-driven discovery of Green’s functions with human-understandable deep learning (Boulle 2022)
  • https://phys.org/news/2022-04-rational-neural-network-advances-partial.html
• #PAPER OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms (Zhuang 2022)
  • #CODE https://git.openi.org.cn/OpenMedIA
  • OpenMedIA is an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous AI computing platforms
• #PAPER Leakage and the Reproducibility Crisis in ML-based Science (Kapoor 2022)
  • Could machine learning fuel a reproducibility crisis in science?
• #PAPER Journal Impact Factor and Peer Review Thoroughness and Helpfulness: A Supervised Machine Learning Study (Severin 2022)
• #PAPER Galactica: A Large Language Model for Science (2022)
  • Paper explained
  • #CODE https://github.com/paperswithcode/galai
  • https://galactica.org/
• #PAPER How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study (2023)
• #PAPER SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning (2024)
  • #CODE GitHub - lamm-mit/SciAgentsDiscovery
  • Built with Autogen
• #PAPER Artificial intelligence and scientific discovery: a model of prioritized search - ScienceDirect (2024)
• #PAPER Artificial Intelligence, Scientific Discovery, and Product Innovation (2024)