Information and images related to 6D-Pose Anchor-based Category-level Keypoint-tracker (6-PACK)
Machine Learning Research

Deep Learning for Object Tracking

AI is good at tracking objects in two dimensions. A new model processes video from a camera with a depth sensor to predict how objects move through space.
2 min read
Results of a technique that interprets reflected light to reveal objects outside the line of sight
Machine Learning Research

Periscope Vision

Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.
2 min read
Different examples of FaceShifter working on peoples' portraits
Machine Learning Research

Trading Faces

AI’s ability to transfer a person’s face from a source photo onto someone in a target photo doesn’t work so well when the target face is partially obscured by, say, eyeglasses, a veil, or a hand. A new technique handles such occlusions.
2 min read
Heart shape made with two hands
Machine Learning Research

That Swipe-Right Look

In an online dating profile, the photo that highlights your physical beauty may not be the one that makes you look smart or honest — also important traits in a significant other. A new neural network helps pick the most appealing shots.
2 min read
Two pandas eating
Machine Learning Research

What Love Sounds Like

Female giant pandas are fertile for only 24 to 36 hours a year: Valentine’s Day on steroids. A new neural network alerts human keepers when a panda couple mates.
1 min read
Data related to AlphaFold
Machine Learning Research

Protein Shapes Revealed

A protein’s biological function depends largely on its three-dimensional shape, but deducing its shape from its sequence of amino acids has been a longstanding problem. Researchers at DeepMind reveal how they used deep learning to solve the puzzle.
2 min read
Information related to Differentiable Digital Signal Processing (DDSP)
Machine Learning Research

Old Tools for New Synths

Neural audio synthesizers like WaveRNN or GANSynth produce impressive sounds, but they require large, data-hungry neural networks. A new code library beefs up the neural music studio with efficient sound modules based on traditional synthesizer designs.
2 min read
Information related to the kNN-LM algorithm
Machine Learning Research

Helpful Neighbors

School teachers may not like to hear this, but sometimes you get the best answer by peeking at your neighbor’s paper. A new language model framework peeks at the training data for context when making a prediction.
2 min read
Information related to FastSpeech, a text-to-speech system
Machine Learning Research

Text to Speech in Parallel

A new system marks a step forward in converting text to speech: It’s fast at inference, reduces word errors, and provides some control over the speed and inflection of generated speech.What’s new: Yi Ren, Yangjun Ruan, and their co-authors at Zhejiang
2 min read
Information related to Greedy InfoMax (GIM)
Machine Learning Research

Better Than Backprop

End-to-end backpropagation and labeled data are the peanut butter and chocolate of deep learning. However, recent work suggests that neither is necessary to train effective neural networks to represent complex data.
2 min read
Graph related to Mixture of Softmaxes (MoS)
Machine Learning Research

Upgrading Softmax

Softmax commonly computes probabilities in a classifier’s output layer. But softmax isn’t always accurate in complex tasks — say, in a natural-language task, when the length of word vectors is much smaller than the number of words in the vocabulary.
2 min read
Math equations represented as trees
Machine Learning Research

Neural Networks Study Math

In tasks that involve generating natural language, neural networks often map an input sequence of words to an output sequence of words. Facebook researchers used a similar technique on sequences of mathematical symbols, training a model to map math problems to math solutions.
2 min read
Maze action video game Pac-Man
Machine Learning Research

Two-Way Winner

AlphaGo Zero demonstrates superhuman performance playing Go, chess, and shogi. Models like R2D2 do the same playing classic Atari titles. A new approach to deep reinforcement learning is the first to achieve state-of-the-art results playing both board and video games.
2 min read
Single Headed Attention RNN (SHA-RNN)
Machine Learning Research

Language Modeling on One GPU

The latest large, pretrained language models rely on trendy layers based on transformer networks. New research shows that these newfangled layers may not be necessary.
2 min read
EfficientDet explained
Machine Learning Research

Easy on the Eyes

Researchers aiming to increase accuracy in object detection generally enlarge the network, but that approach also boosts computational cost. A novel architecture sets a new state of the art in accuracy while cutting the compute cycles required.
2 min read

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox