As spiking neural networks receive more attention, we look toward applications of this computing paradigm in fields other than computer vision and signal processing. One major field, underexplored in the neuromorphic setting, is Natural Language Processing (NLP), where most state-of-the-art solutions still heavily rely on resource-consuming and power-hungry traditional deep learning architectures. Therefore, it is compelling to design NLP models for neuromorphic architectures due to their low energy requirements, with the additional benefit of a more human-brain-like operating model for processing information. However, one of the biggest issues with bringing NLP to the neuromorphic setting is in properly encoding text into a spike train so that it can be seamlessly handled by both current and future SNN architectures. In this paper, we compare various methods of encoding text as spikes and assess each method's performance in an associated SNN on a downstream NLP task, namely, sentiment analysis. Furthermore, we go on to propose a new method of encoding text as spikes that outperforms a widely-used rate-coding technique, Poisson rate-coding, by around 13\% on our benchmark NLP tasks. Subsequently, we demonstrate the energy efficiency of SNNs implemented in hardware for the sentiment analysis task compared to traditional deep neural networks, observing an energy efficiency increase of more than 32x during inference and 60x during training while incurring the expected energy-performance tradeoff.

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more energy-efficient algorithms and hardware solutions. This work addresses the growing energy consumption problem in Machine Learning (ML), particularly during the inference phase. Even a slight reduction in power usage can lead to significant energy savings, benefiting users, companies, and the environment. Our approach focuses on maximizing the accuracy of Artificial Neural Network (ANN) models using a neuroevolutionary framework whilst minimizing their power consumption. To do so, power consumption is considered in the fitness function. We introduce a new mutation strategy that stochastically reintroduces modules of layers, with power-efficient modules having a higher chance of being chosen. We introduce a novel technique that allows training two separate models in a single training step whilst promoting one of them to be more power efficient than the other while maintaining similar accuracy. The results demonstrate a reduction in power consumption of ANN models by up to 29.2% without a significant decrease in predictive performance.

The Copernicus Regional Reanalysis for Europe, CERRA, is a high-resolution regional reanalysis dataset for the European domain. In recent years it has shown significant utility across various climate-related tasks, ranging from forecasting and climate change research to renewable energy prediction, resource management, air quality risk assessment, and the forecasting of rare events, among others. Unfortunately, the availability of CERRA is lagging two years behind the current date, due to constraints in acquiring the requisite external data and the intensive computational demands inherent in its generation. As a solution, this paper introduces a novel method using diffusion models to approximate CERRA downscaling in a data-driven manner, without additional informations. By leveraging the lower resolution ERA5 dataset, which provides boundary conditions for CERRA, we approach this as a super-resolution task. Focusing on wind speed around Italy, our model, trained on existing CERRA data, shows promising results, closely mirroring original CERRA data. Validation with in-situ observations further confirms the model's accuracy in approximating ground measurements.

Large Language Models (LLMs) have demonstrated remarkable capabilities in important tasks such as natural language understanding, language generation, and complex reasoning and have the potential to make a substantial impact on our society. Such capabilities, however, come with the considerable resources they demand, highlighting the strong need to develop effective techniques for addressing their efficiency challenges.In this survey, we provide a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from model-centric, data-centric, and framework-centric perspective, respectively. We have also created a GitHub repository where we compile the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey, and will actively maintain this repository and incorporate new research as it emerges. We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field.

Log data can reveal valuable information about how users interact with Web search services, what they want, and how satisfied they are. However, analyzing user intents in log data is not easy, especially for emerging forms of Web search such as AI-driven chat. To understand user intents from log data, we need a way to label them with meaningful categories that capture their diversity and dynamics. Existing methods rely on manual or machine-learned labeling, which are either expensive or inflexible for large and dynamic datasets. We propose a novel solution using large language models (LLMs), which can generate rich and relevant concepts, descriptions, and examples for user intents. However, using LLMs to generate a user intent taxonomy and apply it for log analysis can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop. To address this, we propose a new methodology with human experts and assessors to verify the quality of the LLM-generated taxonomy. We also present an end-to-end pipeline that uses an LLM with human-in-the-loop to produce, refine, and apply labels for user intent analysis in log data. We demonstrate its effectiveness by uncovering new insights into user intents from search and chat logs from the Microsoft Bing commercial search engine. The proposed work's novelty stems from the method for generating purpose-driven user intent taxonomies with strong validation. This method not only helps remove methodological and practical bottlenecks from intent-focused research, but also provides a new framework for generating, validating, and applying other kinds of taxonomies in a scalable and adaptable way with minimal human effort.

Accurate crop type maps are an essential source of information for monitoring yield progress at scale, projecting global crop production, and planning effective policies. To date, however, crop type maps remain challenging to create in low and middle-income countries due to a lack of ground truth labels for training machine learning models. Field surveys are the gold standard in terms of accuracy but require an often-prohibitively large amount of time, money, and statistical capacity. In recent years, street-level imagery, such as Google Street View, KartaView, and Mapillary, has become available around the world. Such imagery contains rich information about crop types grown at particular locations and times. In this work, we develop an automated system to generate crop type ground references using deep learning and Google Street View imagery. The method efficiently curates a set of street view images containing crop fields, trains a model to predict crop type by utilizing weakly-labelled images from disparate out-of-domain sources, and combines predicted labels with remote sensing time series to create a wall-to-wall crop type map. We show that, in Thailand, the resulting country-wide map of rice, cassava, maize, and sugarcane achieves an accuracy of 93%. We publicly release the first-ever crop type map for all of Thailand 2022 at 10m-resolution with no gaps. To our knowledge, this is the first time a 10m-resolution, multi-crop map has been created for any smallholder country. As the availability of roadside imagery expands, our pipeline provides a way to map crop types at scale around the globe, especially in underserved smallholder regions.

A group of scientists from across the U.S. claim to have created the first artificial intelligence capable of generating AI without human supervision. North Korea has been developing artificial intelligence across various sectors, including in military technology and programs that safeguard nuclear reactors, which could create international threats, according to a new report. The authoritarian regime has used AI to develop wargame simulations and has collaborated with Chinese tech researchers, according to a report by 38 North, a publication for policy and technical analysis of North Korean affairs. The AI advancements and foreign collaboration could lead to sanction violations and leaked information, the report stated. North Korea has been rapidly developing artificial intelligence for a myriad of civilian and military uses, according to a new report.

Leo Prieto's passion for nature started during his childhood by the sea. "I was obsessed with what was under the surface. I'd anchor myself to a rock with my snorkel, and I was fascinated by all the little animals doing things that go unnoticed." His teenage years coincided with the arrival of the internet in Chile, where he became a web pioneer, launching and selling several startups. Inevitably, his interests in the environment, the internet and business merged, driven by the feeling that technological advances should not be wasted.

We start 2024 with a packed monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we continue our coverage of NeurIPS, meet the first interviewee in our AAAI Doctoral Consortium series, and find out how to build AI openly. The AAAI/SIGAI Doctoral Consortium provides an opportunity for a group of PhD students to discuss and explore their research interests and career objectives in an interdisciplinary workshop together with a panel of established researchers. Over the course of the next few months, we'll be meeting the participants and finding out more about their work, PhD life, and their future research plans. In the first interview of the series, Changhoon Kim told us about his research on enhancing the reliability of image generative AI.

However, it is still challenging to solve practical problems such as blood flows, atmospheric and ocean currents, wildfires, and wind turbines because of their multiscale nature. Resolving all scales is computationally infeasible. As a result, physical modeling is typically carried out on a coarse grid using the appropriate subgrid-scale (SGS) models. For example, large eddy simulation (LES) resolves large-scale turbulent motion on a grid, which carries most of the flow energy, while modeling the small scales that have relatively little influence on the mean flow [8]. The goal of SGS models is to capture the effect of the small-scale structures that cannot be resolved in the grid on the resolved scales and to guarantee numerical stability [9]. The static Smagorinsky model [10] and dynamic Smagorinsky model [11], which predict the dissipation of SGS energy, are the most widely used SGS models for turbulence. In high-order DG methods, both Collis [12] and Sengupta et al. [13] successfully used the static Smagorinksy model and dynamic Smagorinsky model, respectively. However, these Smagorinsky models perform poorly for certain flows [14, 15] because they are based on the assumption that eddy viscosity is always purely dissipative and thus are unable to account for energy flow from small scales to large scales (backscatter) [16, 11]. Alternatively, numerical dissipation can be used for modeling unresolved scales as an implicit SGS model.