generalization – Page 5 – Andrew Fairless, Ph.D.

What I Read: Building Robust Machine Learning Systems

By Andrew Fairless on February 19, 2021January 20, 2021

https://medium.com/swlh/deepminds-three-pillars-for-building-robust-machine-learning-systems-a9679e56250a DeepMind’s Three Pillars for Building Robust Machine Learning SystemsSpecification Testing, Robust Training and Formal Verification are three elements that the AI powerhouse believe hold the essence of robust machineContinue readingWhat I Read: Building Robust Machine Learning Systems

What I Read: The way we train AI is flawed

By Andrew Fairless on February 15, 2021January 18, 2021

https://www.technologyreview.com/2020/11/18/1012234/training-machine-learning-broken-real-world-heath-nlp-computer-vision/ The way we train AI is fundamentally flawedThe process used to build most of the machine-learning models we use today can’t tell if they will work in the realContinue readingWhat I Read: The way we train AI is flawed

What I Read: Explainable AI, 2-Stage Approach

By Andrew Fairless on February 5, 2021January 10, 2021

https://www.kdnuggets.com/2020/10/explaining-explainable-ai.html Explaining the Explainable AI: A 2-Stage ApproachBy Amit Dhurandhar, Research Scientist at IBM. “XAI is primarily concerned with understanding or interpreting the decisions made by these opaque or black-boxContinue readingWhat I Read: Explainable AI, 2-Stage Approach

What I Read: Neural Networks Help Explain Brains

By Andrew Fairless on February 1, 2021January 7, 2021

https://www.quantamagazine.org/deep-neural-networks-help-to-explain-living-brains-20201028/ neuroscienceDeep Neural Networks Help to Explain Living Brains Deep neural networks, often criticized as “black boxes,” are helping neuroscientists understand the organization of living brains.“If their CNN mimicked aContinue readingWhat I Read: Neural Networks Help Explain Brains

What I Read: Can a neural network train other networks?

By Andrew Fairless on January 31, 2021January 6, 2021

https://towardsdatascience.com/can-a-neural-network-train-other-networks-cf371be516c6?gi=4765ee11be44 Can a neural network train other networks?An introduction to knowledge distillationTivadar DankaOct 5 “Now you have a huge model, which, although performs excellently, there is no way to deployContinue readingWhat I Read: Can a neural network train other networks?

What I Read: AI’s limitations

By Andrew Fairless on January 26, 2021December 31, 2020

https://www.economist.com/technology-quarterly/2020/06/11/an-understanding-of-ais-limitations-is-starting-to-sink-in Technology QuarterlyJun 11th 2020 editionAn understanding of AI’s limitations is starting to sink inAfter years of hype, many people feel AI has failed to deliver, says Tim Cross “SurveyingContinue readingWhat I Read: AI’s limitations

What I Read: Continual Learning… and the Bridge to Active and Open World Learning

By Andrew Fairless on January 22, 2021December 30, 2020

https://arxiv.org/abs/2009.01797 A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World LearningMartin Mundt, Yong Won Hong, Iuliia Pliushch, Visvanathan RameshContinue readingWhat I Read: Continual Learning… and the Bridge to Active and Open World Learning

What I Read: Symbolic Models from Deep Learning

By Andrew Fairless on January 4, 2021December 22, 2020

https://astroautomata.com/paper/symbolic-neural-nets/ Discovering Symbolic Models from Deep Learning with Inductive BiasesPaper Code Interactive NotebookPaper authors: Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho “…when doesContinue readingWhat I Read: Symbolic Models from Deep Learning

What I Read: sub-linear deep learning algorithm

By Andrew Fairless on December 19, 2020December 4, 2020

https://www.kdnuggets.com/2020/03/deep-learning-breakthrough-sub-linear-algorithm-no-gpu.html Deep Learning Breakthrough: a sub-linear deep learning algorithm that does not need a GPU?By Anshumali Shrivastava, Rice University. “Backpropagation is not an efficient algorithm…. The core idea behind theContinue readingWhat I Read: sub-linear deep learning algorithm

Tag: generalization