Data and graphs related to teacher networks

Flexible Teachers, Smarter Students: Meta Pseudo Labels improves knowledge distillation.

Human teachers can teach more effectively by adjusting their methods in response to student feedback. It turns out that teacher networks can do the same.
Road sign with the word "trust"

Toward AI We Can Count On: Public trust recommendations from AI researchers

A consortium of top AI experts proposed concrete steps to help machine learning engineers secure the public’s trust. Dozens of researchers and technologists recommended actions to counter public skepticism toward artificial intelligence, fueled by issues like data privacy.
Illustration of a patient in a hospital bed

Prognosis — Early Warning for Sepsis: AI can provide an early warning for sepsis.

An AI-driven alarm system helps rescue patients before infections become fatal. The problem: Machine learning can spot patterns in electronic health data indicating where a patient’s condition is headed that may be too subtle for doctors and nurses to catch.
Information and data related to the meta-algorithm AutoML-Zero

Beyond Neural Architecture Search: AutoML-Zero is a meta-algorithm for classification.

Faced with a classification task, an important step is to browse the catalog of machine learning architectures to find a good performer. Researchers are exploring ways to do it automatically.
Schematic of a typical deep learning workflow

(Science) Community Outreach: A survey of machine learning from Eric Schmidt

Are your scientist friends intimidated by machine learning? They might be inspired by a primer from one of the world’s premier tech titans. Former Google CEO Eric Schmidt and Cornell PhD candidate Maithra Raghu school scientists in machine learning in a sprawling overview.
Quantum computing

Quantum Leap: Researchers build TensorFlow hardware for quantum computing.

Quantum computing has made great strides in recent years, though it still faces significant challenges. If and when it gets here, machine learning may be ready for it.
Graph related to imple Contrastive Learning (SimCLR)

Self-Supervised Simplicity: Image classification with simple contrastive learning (SimCLR)

A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.
FixMatch example

Less Labels, More Learning: Improved small data performance with combined techniques

In small data settings where labels are scarce, semi-supervised learning can train models by using a small number of labeled examples and a larger set of unlabeled examples. A new method outperforms earlier techniques.
Simplified depiction of LSH Attention

Transformers Transformed: Research improves transformer efficiency with Reformer.

Transformer networks have revolutionized natural language processing, but they hog processor cycles and memory. New research demonstrates a more frugal variation.
Association for the Advancement of Artificial Intelligence conference in New York

Meeting of the Minds: Deep learning pioneers discuss the state of AI.

Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.
Capture of a chatbot telling jokes developed by Google Brain

Bot Comic: How Google's Meena chatbot developed a sense of humor

Androids may not dream of electric sheep, but some crack jokes about horses and cows. Meena, a 2.6-billion parameter chatbot developed by Google Brain, showed impressive conversational ability, discussing a variety of topics.
Graph related to Mixture of Softmaxes (MoS)

Upgrading Softmax: Mixtape is a faster way to avoid the softmax bottleneck.

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.
Breast cancer screening

Cancer in the Crosshairs: Experts criticize and AI study for analyzing mammograms.

Computer vision has potential to spot cancer earlier and more accurately than human experts. A new system surpassed human accuracy in trials, but critics aren’t convinced.
EfficientDet explained

Easy on the Eyes: More accurate object detection with EfficientDet

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.
Illustration of a fireplace with "Happy holidays" cards in English, Spanish and French

Natural Language Processing Models Get Literate: Why 2019 was a breakthrough year for NLP

Earlier language models powered by Word2Vec and GloVe embeddings yielded confused chatbots, grammar tools with middle-school reading comprehension, and not-half-bad translations. The latest generation is so good, some people consider it dangerous.

Subscribe to The Batch

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