Explanation of Multi-Modal Delay Randomization (MMDR)
Machine Learning Research

Coordinating Robot Limbs: Machine learning improves robot dog reaction time.

A dog doesn’t think twice about fetching a tennis ball, but an autonomous robot typically suffers from delays between perception and action. A new machine-learning model helped a quadruped robot coordinate its sensors and actuators.
Schematic of the model architecture showing the generator with spatial latent vectors
Machine Learning Research

Weather Forecast by GAN: GAN improves short-term rainfall predictions.

A new deep learning technique increased the precision of short-term rainfall forecasts. Researchers developed the Deep Generative Model of Radar (DGMR) to predict amounts of precipitation up to two hours in advance.
Illustration of how different data split strategies partition the labelled data
Machine Learning Research

Fine-Tune Your Fine-Tuning: New method optimizes training for few shot NLP models.

Let’s say you have a pretrained language model and a small amount of data to fine-tune it to answer yes-or-no questions. Should you fine-tune it to classify yes/no or to fill in missing words — both viable approaches that are likely to yield different results?
 Service oriented architecture (SOA) implementation of the Ride Allocation app
Machine Learning Research

To Flow or Not to Flow: Building more efficient networked machine learning.

Networked software is often built using a service-oriented architecture, but networked machine learning applications may be easier to manage using a different programming style.
Diagram with info about AlphaCode
Machine Learning Research

Competitive Coder: AI code writing system can compete alongside humans.

Programming is hard. Programming competitions are harder. Yet transformers proved themselves up to the task.
The performance of different downstream (DS)
Machine Learning Research

The Limits of Pretraining: More pretraining doesn't guarantee a better fine-tuned AI.

The higher the accuracy of a pretrained model, the better its performance after fine-tuning, right? Not necessarily. Researchers conducted a meta-analysis of image-recognition experiments and performed some of their own.
Fake face diagram - FaceSynthetics
Machine Learning Research

Fake Faces Are Good Training Data: Synthetic data improves face recognition performance.

Collecting and annotating a dataset of facial portraits is a big job. New research shows that synthetic data can work just as well.
Diagram with automated decision systems
Machine Learning Research

Roadblocks to Regulation: Why laws to regulate AI usually fail.

Most U.S. state agencies use AI without limits or oversight. An investigative report probed reasons why efforts to rein them in have made little headway. Since 2018, nearly every proposed bill aimed at studying or controlling how state agencies use automated decision systems.
Transformer Architecture
Machine Learning Research

Transformers See in 3D: Using transformers to visualize depth in 2D images.

Visual robots typically perceive the three-dimensional world through sequences of two-dimensional images, but they don’t always know what they’re looking at. For instance, Tesla’s self-driving system has been known to mistake a full moon for a traffic light.
Overview of Mobile-Former | Cross attention over the entire featuremap for the first token in Mobile→Former
Machine Learning Research

High Accuracy at Low Power: An energy efficient method for computer vision.

Equipment that relies on computer vision while unplugged — mobile phones, drones, satellites, autonomous cars — need power-efficient models. A new architecture set a record for accuracy per computation.
Schematic of 8-bit optimizers via block-wise dynamic quantization
Machine Learning Research

More Learning With Less Memory: Training large language models using less memory.

Researchers discovered a new way to reduce memory requirements when training large machine learning models. Tim Dettmers and colleagues at University of Washington released 8-bit optimizers that store gradient statistics as 8-bit values, while maintaining the same accuracy.
Tax planning model AI Economist
Machine Learning Research

Tax Relief the AI Way: AI Economist creates optimal tax rate.

Nothing is certain except death and taxes, the saying goes — but how to make taxes fair and beneficial remains an open question. New research aims to answer it.
Graphs
Machine Learning Research

Why Active Learning Fails: Pairing active learning with visual question answering.

Where labeled training data is scarce, an algorithm can learn to request labels for key examples. While this practice, known as active learning, can supply labeled examples that improve performance in some tasks, it fails in others.
Equivariant subsampling on 1D feature maps with a scale factor c = 2.
Machine Learning Research

Image Transformations Unmasked: CNNs for vision that aren't fooled by changing backgrounds.

If you change an image by moving its subject within the frame, a well trained convolutional neural network may not recognize the fundamental similarity between the two versions. New research aims to make CNN wise to such alterations.
Two images showing RETRO Architecture and Gopher (280B) vs State of the Art
Machine Learning Research

Large Language Models Shrink: Gopher and RETRO prove lean language models can push boundaries.

DeepMind released three papers that push the boundaries — and examine the issues — of large language models.

Subscribe to The Batch

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