Six-Word Sci-Fi: Stories Written by You
Here’s this month’s prompt, how to submit, and an illustrated archive of past favorites.
Is ‘Green Capitalism’ Total BS?
In The Value of a Whale, author Adrienne Buller argues forcefully against market-based “solutions” to the climate crisis. She thinks we can do better.
AI models can now continually learn from new data on intelligent edge devices like smartphones and sensors
A new technique enables on-device training of machine-learning models on edge devices like microcontrollers, which have very limited memory. This could allow edge devices to continually learn from new data, eliminating data privacy issues, while enabling user customization.
New algorithms help four-legged robots run in the wild
A new system of algorithms enables four-legged robots to walk and run on challenging terrain while avoiding both static and moving obstacles. The work brings researchers a step closer to building robots that can perform search and rescue missions or collect information in places that are too dangerous or difficult for humans.
New technique enables on-device training using less than a quarter of a megabyte of memory
Microcontrollers, miniature computers that can run simple commands, are the basis for billions of connected devices, from internet-of-things (IoT) devices to sensors in automobiles. But cheap, low-power microcontrollers have extremely limited memory and no operating system, making it challenging to train artificial intelligence models on “edge devices” that work independently from central computing resources.
New algorithms help four-legged robots run in the wild
A team led by the University of California San Diego has developed a new system of algorithms that enables four-legged robots to walk and run on challenging terrain while avoiding both static and moving obstacles.
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
A central issue in machine learning is how to train models on sensitive user data. Industry has widely adopted a simple algorithm: Stochastic Gradient Descent with noise (a.k.a. Stochastic Gradient Langevin Dynamics). However, foundational theoretical questions about this algorithm’s privacy loss remain open — even in the seemingly simple setting of smooth convex losses over …
Read more “Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss”
3D Parametric Room Representation with RoomPlan
FLAIR: Federated Learning Annotated Image Repository
Cross-device federated learning is an emerging machine learning (ML) paradigm where a large population of devices collectively train an ML model while the data remains on the devices. This research field has a unique set of practical challenges, and to systematically make advances, new datasets curated to be compatible with this paradigm are needed. Existing …
Read more “FLAIR: Federated Learning Annotated Image Repository”
Two-Layer Bandit Optimization for Recommendations
Online commercial app marketplaces serve millions of apps to billions of users in an efficient manner. Bandit optimization algorithms are used to ensure that the recommendations are relevant, and converge to the best performing content over time. However, directly applying bandits to real-world systems, where the catalog of items is dynamic and continuously refreshed, is …
Read more “Two-Layer Bandit Optimization for Recommendations”