neural network – Page 20 – Andrew Fairless, Ph.D.

What I Read: Continual Learning, Amnesia, Neural Networks

By Andrew Fairless on March 22, 2021March 7, 2021

https://medium.com/dataseries/ibm-uses-continual-learning-to-avoid-the-amnesia-problem-in-neural-networks-ae8241e1f3a3 IBM Uses Continual Learning to Avoid The Amnesia Problem in Neural NetworksUsing continual learning might avoid the famous catastrophic forgetting problem in neural networks.Jesus RodriguezJan 25 “Building neural networksContinue readingWhat I Read: Continual Learning, Amnesia, Neural Networks

What I Read: Deep learning, black box

By Andrew Fairless on March 21, 2021March 7, 2021

https://bdtechtalks.com/2021/01/11/concept-whitening-interpretable-neural-networks/ Deep learning doesn’t need to be a black boxBen DicksonJanuary 11, 2021 “The innerworkings of neural networks are often a mystery…. scientists at Duke University propose “concept whitening,” aContinue readingWhat I Read: Deep learning, black box

What I Read: Adversarial generation of extreme samples

By Andrew Fairless on March 19, 2021March 7, 2021

https://aihub.org/2020/10/01/adversarial-generation-of-extreme-samples/ Adversarial generation of extreme samplesby Lucy SmithOctober 1, 2020 “…existing GAN-based methods tend to generate typical samples.. the authors seek to design deep learning-based models that can generate samplesContinue readingWhat I Read: Adversarial generation of extreme samples

What I Read: Ensemble, knowledge distillation, and self-distillation

By Andrew Fairless on March 16, 2021March 7, 2021

https://www.microsoft.com/en-us/research/blog/three-mysteries-in-deep-learning-ensemble-knowledge-distillation-and-self-distillation/ Three mysteries in deep learning: Ensemble, knowledge distillation, and self-distillationPublished January 19, 2021By Zeyuan Allen-Zhu , Senior Researcher Yuanzhi Li , Assistant Professor, Carnegie Mellon University “…besides this smallContinue readingWhat I Read: Ensemble, knowledge distillation, and self-distillation

What I Read: ML Models are Missing Contracts

By Andrew Fairless on March 15, 2021March 7, 2021

https://gradio.app/blog/missing-contracts Machine Learning Models are Missing ContractsWhy pretrained machine learning models are often unusable and irreproducible — and what we can do about it.By Abubakar Abid “We need to provideContinue readingWhat I Read: ML Models are Missing Contracts

What I Read: Transformer Networks to Answer Questions About Images

By Andrew Fairless on March 13, 2021March 7, 2021

https://medium.com/dataseries/microsoft-uses-transformer-networks-to-answer-questions-about-images-with-minimum-training-f978c018bb72 Microsoft Uses Transformer Networks to Answer Questions About Images With Minimum TrainingUnified VLP can understand concepts about scenic images by using pretrained models.Jesus RodriguezJan 12 “Can we build deepContinue readingWhat I Read: Transformer Networks to Answer Questions About Images

What I Read: Interpretation for Image Recognition

By Andrew Fairless on March 12, 2021March 7, 2021

https://thegradient.pub/a-visual-history-of-interpretation-for-image-recognition/ A Visual History of Interpretation for Image Recognition16.Jan.2021by Ali Abdalla “…during the last decade, researchers developed many different methods to open the “black box” of deep learning, aiming toContinue readingWhat I Read: Interpretation for Image Recognition

What I Read: Neural Text Generation

By Andrew Fairless on March 11, 2021March 7, 2021

https://lilianweng.github.io/lil-log/2021/01/02/controllable-neural-text-generation.html Controllable Neural Text GenerationJan 2, 2021Lilian Weng “How to steer a powerful unconditioned language model? In this post, we will delve into several approaches for controlled content generation withContinue readingWhat I Read: Neural Text Generation

What I Read: Why I’m lukewarm on graph neural networks

By Andrew Fairless on March 10, 2021March 7, 2021

https://www.singlelunch.com/2020/12/28/why-im-lukewarm-on-graph-neural-networks/ Why I’m lukewarm on graph neural networksMatt RangerFebruary 16, 2020 “I’m only lukewarm on Graph Neural Networks (GNNs)…. I think some progress can come of this research, but we’reContinue readingWhat I Read: Why I’m lukewarm on graph neural networks

What I Read: How Transformers work

By Andrew Fairless on March 9, 2021March 7, 2021

https://theaisummer.com/transformer/ How Transformers work in deep learning and NLP: an intuitive introductionNatural Language ProcessingNikolas AdaloglouDec 24, 2020 “In my opinion, transformers are not so hard to grasp. It’s the combinationContinue readingWhat I Read: How Transformers work

Tag: neural network