Referenced Papers (30)
The perceptron: a probabilistic model for information storage and organization in the brain
F Rosenblatt
Psychol. Rev., 1958
"The speaker introduces the "Perceptron" as the foundational unit for artificial intelligence, a model of how neurons operate in the brain, which was the start of the field."
Learning representations by back-propagating errors
D Rumelhart, Geoffrey E Hinton, Ronald J Williams
Nature, 1986
"This paper is cited to introduce multi-layer perceptrons (MLPs) as a more complex architecture that can solve problems that single-layer perceptrons cannot, such as the continuous XOR problem."
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei
, 2009
"This citation refers to the ImageNet dataset, a massive, widely available dataset that was crucial for developing and training convolutional neural network algorithms for image classification."
An analysis of deep neural network models for practical applications
A Canziani, Adam Paszke, E Culurciello
ArXiv, 2016
"The speaker uses a figure from this paper to illustrate the trend that more complex deep neural network architectures (with more operations) generally achieve better performance on image classification tasks like ImageNet."
CNN features off-the-shelf: An astounding baseline for recognition
A Razavian, Hossein Azizpour, Josephine Sullivan, S Carlsson
2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014
"This citation is presented alongside the concept of "pre-training" to explain how features learned by a model on a large dataset (like ImageNet) can be effectively transferred to a new task with a smaller dataset, a key technique in medical AI."
Dermatologist-level classification of skin cancer with deep neural networks
Andre Esteva, Brett Kuprel, Roberto A Novoa, Justin Ko, Susan M Swetter, Helen M Blau
Nature, 2017
"The speaker presents this as a seminal paper in medical AI, showing that a pre-trained deep neural network could classify skin cancer from dermatological images with performance on par with expert dermatologists."
CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning
Pranav Rajpurkar, J Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan
ArXiv, 2017
"This paper is cited as another example of AI achieving expert-level performance in medicine, specifically in detecting pneumonia from chest X-rays and even localizing the important regions, which sparked discussions about AI replacing radiologists."
Fully convolutional networks for semantic segmentation
Evan Shelhamer, Jonathan Long, Trevor Darrell
IEEE Trans. Pattern Anal. Mach. Intell., 2017
"This paper introduced Fully Convolutional Networks (FCNs), an architecture for image segmentation that classifies every pixel in an image, allowing for more detailed and localized analysis than simple image classification."
U-Net: Convolutional Networks for Biomedical Image Segmentation
O Ronneberger, P Fischer, T Brox
Medical Image Computing and Computer-Assisted Intervention, 2015
"The speaker introduces the U-Net architecture as a key innovation specifically for biomedical image segmentation, which efficiently handles large medical images by compressing them into a memory-efficient representation to capture global features."
3D U-net: Learning dense volumetric segmentation from sparse annotation
Özgün Çiçek, A Abdulkadir, S Lienkamp, T Brox, O Ronneberger
Medical Image Computing and Computer-Assisted Intervention, 2016
"This paper is cited as an extension of the U-Net architecture to 3D, allowing for volumetric segmentation of 3D medical images like MRI or confocal scans."
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
Fabian Isensee, Paul F Jaeger, Simon A A Kohl, Jens Petersen, Klaus H Maier-Hein
Nat. Methods, 2021
"This work is presented as a general-purpose iteration on the U-Net architecture, designed to handle a wide variety of medical segmentation tasks such as vascular or tumor segmentation."
Space-time wiring specificity supports direction selectivity in the retina
Jinseop S Kim, M Greene, A Zlateski, Kisuk Lee, Mark Richardson, Srinivas C Turaga
Nature, 2014
"The speaker uses this paper as an example of neural circuit reconstruction, where convolutional neural networks are used to trace individual neurons through electron microscopy data to create 3D reconstructions of brain tissue."
Unsupervised representation learning with deep convolutional generative adversarial networks
Alec Radford, Luke Metz, Soumith Chintala
Int Conf Learn Represent, 2015
"This paper is cited to explain Generative Adversarial Networks (GANs), a key architecture in generative AI where a "generator" and a "discriminator" network compete to produce realistic fake images."
Image-to-image translation with conditional adversarial networks
Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A Efros
Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016
"This work is cited to introduce conditional GANs (cGANs) for image-to-image translation, where the generation of an image is conditioned on another image, such as creating a realistic photo from a sketch."
A neural algorithm of artistic style
Leon A Gatys, Alexander S Ecker, M Bethge
ArXiv, 2015
"This paper is referenced for its work on "style transfer," a generative AI technique that applies the artistic style of one image to the content of another."
Deep generative medical image harmonization for improving cross‐site generalization in deep learning predictors
V Bashyam, J Doshi, G Erus, D Srinivasan, A Abdulkadir, Ashish Singh
J. Magn. Reson. Imaging, 2021
"The speaker cites this paper as an application of style transfer to solve the problem of medical image harmonization, where AI is used to make images from different scanners or hospitals look consistent."
MedGAN: Medical Image Translation using GANs
Karim Armanious, Chenming Yang, Marc Fischer, T Küstner, K Nikolaou, S Gatidis
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2018
"This paper is cited to explain domain adaptation, a technique where GANs are used to translate images from one modality to another (e.g., PET to CT), potentially augmenting datasets or replacing more expensive imaging methods."
BABEL enables cross-modality translation between multiomic profiles at single-cell resolution
Kevin E Wu, K Yost, Howard Y Chang, James Zou
Proc. Natl. Acad. Sci. U. S. A., 2020
"This paper is shown as an example of domain translation beyond images, specifically for translating between different single-cell multiomic profiles, like from RNA expression to ATAC profiles."
Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals
Yuzhe Yang, Yuan Yuan, Guo Zhang, Hao Wang, Ying Chen, Yingcheng Liu
News@nat.,Com, 2022
"The speaker highlights this paper as a creative example of integrating disparate datasets, where the model predicts Parkinson's disease from nocturnal breathing by leveraging relationships between breathing, EEG signals, and the disease."
Unsupervised representation learning by predicting image rotations
Spyros Gidaris, Praveer Singh, N Komodakis
Int Conf Learn Represent, 2018
"This paper is used to introduce self-supervised learning, where an AI model learns rich features from unlabeled data by solving a "pretext" task, in this case, predicting the rotation of an image."
Unsupervised visual representation learning by context prediction
Carl Doersch, Abhinav Gupta, Alexei A Efros
arXiv [cs.CV], 2015
"Part of a collage illustrating different "pretext" tasks for self-supervised learning in computer vision, specifically predicting the relative position of image patches."
Context Encoders: Feature learning by inpainting
Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A Efros
arXiv [cs.CV], 2016
"Part of a collage illustrating different "pretext" tasks for self-supervised learning in computer vision."
Unsupervised learning of visual representations by solving Jigsaw puzzles
Mehdi Noroozi, Paolo Favaro
arXiv [cs.CV], 2016
"Part of a collage illustrating different "pretext" tasks for self-supervised learning in computer vision, specifically solving jigsaw puzzles with image patches."
Look, Listen and Learn
Relja Arandjelović, Andrew Zisserman
ICCV, 2017
"This paper is cited to explain multi-modal self-supervised learning, where a model learns by determining if the audio and visual streams of a video correspond, forcing it to understand the relationship between what is seen and what is heard."
Audio-visual modelling in a clinical setting
Jianbo Jiao, Mohammad Alsharid, Lior Drukker, Aris T Papageorghiou, Andrew Zisserman, J Alison Noble
Sci. Rep., 2024
"This paper is presented as a medical application of multi-modal learning, where a model analyzes both the ultrasound video and the sonographer's speech to learn features and predict the sonographer's gaze."
Attention is All you Need
Ashish Vaswani, Noam M Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez
Neural Inf Process Syst, 2017
"This is the seminal paper that introduced the Transformer architecture, a key innovation that powers modern large language models by using an attention mechanism to focus on relevant parts of sequential data."
Matching patients to clinical trials with large language models
Qiao Jin, Zifeng Wang, Charalampos S Floudas, Fangyuan Chen, Changlin Gong, Dara Bracken-Clarke
ArXiv, 2024
"This work demonstrates a practical clinical application of large language models for patient recruitment, using a pre-trained GPT model to match patients to eligible clinical trials based on their notes, significantly reducing clinician screening effort."
A study of generative large language model for medical research and healthcare
C A I Peng, Xi Yang, Aokun Chen, Kaleb E Smith, Nima M Pournejatian, Anthony B Costa
NPJ Digital Medicine, 2023
"This paper is cited in the context of clinical language models (CLaMS), which are large language models specifically trained on clinical notes to better understand medical text."
A study of generative large language model for medical research and healthcare
C A I Peng, Xi Yang, Aokun Chen, Kaleb E Smith, Nima M Pournejatian, Anthony B Costa
NPJ Digital Medicine, 2023
"This work introduced GatorTron, a large clinical language model trained on billions of words from clinical notes, which was shown to generate outputs indistinguishable from expert-written text."
Health system-scale language models are all-purpose prediction engines
L Jiang, Xujin C Liu, Nima Pour Nejatian, Mustafa Nasir-Moin, Duo Wang, Anas Abidin
Nature, 2023
"This paper is cited to show the potential of large language models for outcome prediction, especially for rare conditions where large, specific datasets are unavailable, by leveraging the model's broad contextual understanding from being trained on vast amounts of medical text."