Given real-world constraints on memory and processing time, images are often downsampled before they’re fed into a neural network. But the process removes fine details, and that degrades accuracy. A new technique squeezes images with less compromise.
Given real-world constraints on memory and processing time, images are often downsampled before they’re fed into a neural network. But the process removes fine details, and that degrades accuracy. A new technique squeezes images with less compromise.
Batch normalization is a technique that normalizes layer outputs to accelerate neural network training. But new research shows that it has other effects that may be more important.
Batch normalization is a technique that normalizes layer outputs to accelerate neural network training. But new research shows that it has other effects that may be more important.
A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.
A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.
Every second counts when a patient’s skull is open in the operating room. A new technique based on deep learning can shorten some brain surgeries. During brain cancer operations, surgeons must stop in mid-operation for up to a half hour while a pathologist analyzes the tumor tissue.
Every second counts when a patient’s skull is open in the operating room. A new technique based on deep learning can shorten some brain surgeries. During brain cancer operations, surgeons must stop in mid-operation for up to a half hour while a pathologist analyzes the tumor tissue.
Looking at images, people see outlines before the details within them. A replacement for the traditional convolutional layer decomposes images based on this distinction between coarse and fine features.
Looking at images, people see outlines before the details within them. A replacement for the traditional convolutional layer decomposes images based on this distinction between coarse and fine features.
As neural networks have become more accurate, they’ve also ballooned in size and computational cost. That makes many state-of-the-art models impractical to run on phones and potentially smaller, less powerful devices.
As neural networks have become more accurate, they’ve also ballooned in size and computational cost. That makes many state-of-the-art models impractical to run on phones and potentially smaller, less powerful devices.
Deep learning models can be unwieldy and often impractical to run on smaller devices without major modification. Researchers at Facebook AI Research found a way to compress neural networks with minimal sacrifice in accuracy.
Deep learning models can be unwieldy and often impractical to run on smaller devices without major modification. Researchers at Facebook AI Research found a way to compress neural networks with minimal sacrifice in accuracy.
Neural networks are good at making predictions, but they’re not so good at estimating how certain they are. If the training data set is small and many sets of model parameters fit the data well, for instance, the network may not realize this explicitly, leading to overly confident predictions.
Stay updated with weekly AI News and Insights delivered to your inbox