Information related to Greedy InfoMax (GIM)
Classification

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)
Classification

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
Lifelike video imagery of virtual people made by NEON
Classification

AI Steals CES

Artificial intelligence was everywhere at the biggest, buzziest consumer-technology showcase in the U.S. AI ruled the convention floor at the annual Consumer Electronics Show in Las Vegas, as numerous media outlets proclaimed.
2 min read
Breast cancer screening
Classification

Cancer in the Crosshairs

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.
2 min read
EfficientDet explained
Classification

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
Yann LeCun
Classification

Yann LeCun: Learning From Observation

How is it that many people learn to drive a car fairly safely in 20 hours of practice, while current imitation learning algorithms take hundreds of thousands of hours, and reinforcement learning algorithms take millions of hours? Clearly we’re missing something big.
2 min read
Chelsea Finn
Classification

Chelsea Finn: Robots That Generalize

Many people in the AI community focus on achieving flashy results, like building an agent that can win at Go or Jeopardy. This kind of work is impressive in terms of complexity.
2 min read
Graph related to Noisy Student performance on ImageNet
Classification

Self-Training for Sharper Vision

The previous state-of-the-art image classifier was trained on the ImageNet dataset plus 3.5 billion supplemental images from a different database. A new method achieved higher accuracy with one-tenth as many supplemental examples — and they were unlabeled, to boot.
2 min read
Information related to Bias-Resilient Neural Network (BR-Net)
Classification

Bias Fighter

Sophisticated models trained on biased data can learn discriminatory patterns, which leads to skewed decisions. A new solution aims to prevent neural networks from making decisions based on common biases.
2 min read
Ancient geoglyph analysed by AI
Classification

Prehistoric Pictures Rediscovered

Image analysis guided by AI revealed a 2,000-year-old picture dug into the Peruvian desert. Researchers analyzing aerial imagery shot over Peru found a pattern that looks like a three-horned humanoid holding a staff.
2 min read
Graph related to LIME and SHAP methods
Classification

Bias Goes Undercover

As black-box algorithms like neural networks find their way into high-stakes fields such as transportation, healthcare, and finance, researchers have developed techniques to help explain models’ decisions. New findings show that some of these methods can be fooled.
2 min read
Security robot walking on the street
Classification

What the Watchbot Sees

Knightscope’s security robots look cute. But these cone-headed automatons, which serve U.S. police departments and businesses, are serious surveillance machines.
2 min read
Information related to a model that predicts a chemical's smell
Classification

Nose Job

Predicting a molecule’s aroma is hard because slight changes in structure lead to huge shifts in perception. Good thing deep learning is developing a sense of smell.
2 min read
Volvo car identifying a pedestrian
Classification

Blind Spot

In March 2018, one of Uber’s self-driving cars became the first autonomous vehicle reported to have killed a pedestrian. A new report by U.S. authorities suggests that the accident occurred because the car’s software was programmed to ignore jaywalkers.
2 min read
Nasdaq
Classification

Spotlight on Stock Scammers

The world’s largest stock market is using AI to flag suspicious trading in real time. Nasdaq is testing a deep learning system to monitor trading of ts U.S. equities. Named Chiron, the system watches for behaviors that indicate potential market manipulation.
1 min read

Subscribe to The Batch

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