Fi Mini and Tractive: Which Smart Cat Tracker Should You Buy? For months, I tested Tractive and Fi Mini smart collars on my cat to find the best for activity, sleep, and GPS tracking. Wearable health-monitoring devices, like smart rings, smartwatches, and fitness trackers, help people stay on top of key wellness markers. By providing data on steps, heart rate, sleep, and more, these gadgets allow people to better understand their health, along with the opportunity to improve it with lifestyle shifts. But why should humans have all the fun?

The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce opaque policies that compromise verification, reduce transparency, and impede human oversight. To address this, we introduce BASIL (Best-Action Symbolic Interpretable Learning), a systematic approach for generating symbolic, rule-based policies via online evolutionary search with quality-diversity (QD) optimization. BASIL represents policies as ordered lists of symbolic predicates over state variables, ensuring full interpretability and tractable policy complexity. By using a QD archive, the methodology in the proposed study encourages behavioral and structural diversity between top-performing solutions, while a complexity-aware fitness encourages the synthesis of compact representations. The evolutionary system supports the use of exact constraints for rule count and system adaptability for balancing transparency with expressiveness. Empirical comparisons with three benchmark tasks CartPole-v1, MountainCar-v0, and Acrobot-v1 show that BASIL consistently synthesizes interpretable controllers with compact representations comparable to deep reinforcement learning baselines. Herein, this article introduces a new interpretable policy synthesis method that combines symbolic expressiveness, evolutionary diversity, and online learning through a unifying framework.

Food systems are responsible for a third of human-caused greenhouse gas emissions. We investigate what Large Language Models (LLMs) can contribute to reducing the environmental impacts of food production. We define a typology of design and prediction tasks based on the sustainable food literature and collaboration with domain experts, and evaluate six LLMs on four tasks in our typology. For example, for a sustainable protein design task, food science experts estimated that collaboration with an LLM can reduce time spent by 45% on average, compared to 22% for collaboration with another expert human food scientist. However, for a sustainable menu design task, LLMs produce suboptimal solutions when instructed to consider both human satisfaction and climate impacts. We propose a general framework for integrating LLMs with combinatorial optimization to improve reasoning capabilities. Our approach decreases emissions of food choices by 79% in a hypothetical restaurant while maintaining participants' satisfaction with their set of choices. Our results demonstrate LLMs' potential, supported by optimization techniques, to accelerate sustainable food development and adoption.

We present improved models for the granular detection and sub-classification news media bias in English news articles. We compare the performance of zero-shot versus fine-tuned large pre-trained neural transformer language models, explore how the level of detail of the classes affects performance on a novel taxonomy of 27 news bias-types, and demonstrate how using synthetically generated example data can be used to improve quality.

Media bias detection requires comprehensive integration of information derived from multiple news sources. Sentence-level political bias detection in news is no exception, and has proven to be a challenging task that requires an understanding of bias in consideration of the context. Inspired by the fact that humans exhibit varying degrees of writing styles, resulting in a diverse range of statements with different local and global contexts, previous work in media bias detection has proposed augmentation techniques to exploit this fact. Despite their success, we observe that these techniques introduce noise by over-generalizing bias context boundaries, which hinders performance. To alleviate this issue, we propose techniques to more carefully search for context using a bias-sensitive, target-aware approach for data augmentation. Comprehensive experiments on the well-known BASIL dataset show that when combined with pre-trained models such as BERT, our augmentation techniques lead to state-of-the-art results. Our approach outperforms previous methods significantly, obtaining an F1-score of 58.15 over state-of-the-art bias detection task.

Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed in a rapidly changing \textit{dynamic} environment, where an AI agent needs to quickly learn new instances in a `single pass' from the non-i.i.d (also possibly temporally contiguous/coherent) data streams without suffering from catastrophic forgetting. For practical applicability, we propose a novel lifelong learning approach, which is streaming, i.e., a single input sample arrives in each time step, single pass, class-incremental, and subject to be evaluated at any moment. To address this challenging setup and various evaluation protocols, we propose a Bayesian framework, that enables fast parameter update, given a single training example, and enables any-time inference. We additionally propose an implicit regularizer in the form of snap-shot self-distillation, which effectively minimizes the forgetting further. We further propose an effective method that efficiently selects a subset of samples for online memory rehearsal and employs a new replay buffer management scheme that significantly boosts the overall performance. Our empirical evaluations and ablations demonstrate that the proposed method outperforms the prior works by large margins.

What makes basil so good? Machine learning has been used to create basil plants that are extra-delicious. While we sadly cannot report firsthand on the herb's taste, the effort reflects a broader trend that involves using data science and machine learning to improve agriculture. The researchers behind the AI-optimized basil used machine learning to determine the growing conditions that would maximize the concentration of the volatile compounds responsible for basil's flavor. The study appears in the journal PLOS One today.

What makes basil so good? Machine learning has been used to create basil plants that are extra-delicious. While we sadly cannot report firsthand on the herb's taste, the effort reflects a broader trend that involves using data science and machine learning to improve agriculture. The researchers behind the AI-optimized basil used machine learning to determine the growing conditions that would maximize the concentration of the volatile compounds responsible for basil's flavor. The study appears in the journal PLOS One today.

Highly technical agriculturalists are hoisting their pitchforks, demanding that we embrace their ideas to reshape our unsustainable food system. Whether our reality is a food desert or a farm-to-table paradise, it's time we start paying attention: In order to keep pace with a global population that's expected to surpass 9 billion by 2050, projections show food production would have to increase by 70 percent between 2005/07 and 2050. Researchers at San Francisco-based artificial intelligence company Sentient Technologies are answering the call, working with a major U.S. university to leverage data-powered technologies with the goal of creating ideal food-growing climates in a world disrupted by global warming. Since 2015, the university has been building one such technology: high-tech "food computers." These sensor-packed and actuator-controlled greenhouses were designed to test out growing conditions for various fruits and vegetables.

As climate change makes it more difficult to grow crops in outdoor farms because of heat waves, more frequent storms, and more pests and disease, the researchers envision that climate-controlled, tech-filled greenhouses (which they call "food computers") could be an increasingly useful place to grow food. The technology could also eliminate food miles: Instead of shipping avocados from Mexico to China, a Chinese greenhouse could precisely recreate a Mexican climate in Beijing–or tweak it to create a climate even better for an avocado tree. "It definitely speeds up the timescale by which we can get interesting results," says Arielle Johnson, one of the researchers at MIT Media Lab Open Agriculture Initiative, or OpenAg. "When you talk to [Caleb Harper, the director of OpenAg], he's like, 'Yeah, basil is a fast-growing plant,' but in his terminology, fast-growing is six to eight weeks," says Babak Hodjat, CEO of Sentient, a company that also designs AI to help stock traders find patterns in the market and hospitals predict infections. "That's a long time to wait just to get a data point. So we tried out this methodology where the AI itself decides what are the next set of data points to try out."