Follow the ideas that keep turning up in Hacker News discussions.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski +10
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands.
Ashish Vaswani, Noam Shazeer, Niki Parmar +5
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
Robert Geirhos, Patricia Rubisch, Claudio Michaelis +3
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.
Jonathan Frankle, Michael Carbin
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy.
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever +4
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks.
Kaiming He, Xiangyu Zhang, Shaoqing Ren +1
Deeper neural networks are more difficult to train.
Alex Krizhevsky
I present a new way to parallelize the training of convolutional neural networks across multiple GPUs.
Gary Marcus
Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) deep network model of Imagenet.
Joseph Redmon, Santosh Divvala, Ross Girshick +1
We present YOLO, a new approach to object detection.
Samuel L. Smith, Andrew Brock, Leonard Berrada +1
Many researchers believe that ConvNets perform well on small or moderately sized datasets, but are not competitive with Vision Transformers when given access to datasets on the web-scale.
Shaoqing Ren, Kaiming He, Ross Girshick +1
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations.
Thomas N. Kipf, Max Welling
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.
Jonathan Huang, Vivek Rathod, Chen Sun +8
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform.
Po-Wei Wang, Priya L. Donti, Bryan Wilder +1
Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems.
Arash Vahdat, Jan Kautz
Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep energy-based models are among competing likelihood-based frameworks for deep generative learning.
Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov +9
Convolutional Neural Networks (CNNs) are the go-to model for computer vision.
Volodymyr Mnih, Koray Kavukcuoglu, David Silver +4
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.
Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz +4
The capacity of a neural network to absorb information is limited by its number of parameters.
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov +9
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.
Anh Nguyen, Jason Yosinski, Jeff Clune
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems.
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Despite widespread adoption, machine learning models remain mostly black boxes.
Margaret Mitchell, Simone Wu, Andrew Zaldivar +6
Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment.
Alec Radford, Jong Wook Kim, Chris Hallacy +9
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
Matthew D Zeiler, Rob Fergus
Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark.
Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner +13
We introduce a modern Hopfield network with continuous states and a corresponding update rule.
Robin Rombach, Andreas Blattmann, Dominik Lorenz +2
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh +5
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation.
Alec Radford, Luke Metz, Soumith Chintala
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications.
Christian Ledig, Lucas Theis, Ferenc Huszar +8
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors?