Machinelearningfreaks

Monitoring Urban Changes in Mariupol/Ukraine in 2022/23. (arXiv:2309.08607v1 [cs.CY])

Monitoring Urban Changes in Mariupol/Ukraine in 2022/23. (arXiv:2309.08607v1 [cs.CY]) The ability to constantly monitor urban changes is of large socio-economic interest. Previous works have already shown approaches in this field with the use of Deep Neural Networks (DNNs) and transfer learning. However, they fell short in demonstrating temporal scale outside of either the training o...

Maneuver Decision-Making Through Proximal Policy Optimization And Monte Carlo Tree Search. (arXiv:2309.08611v1 [cs.AI])

Maneuver Decision-Making Through Proximal Policy Optimization And Monte Carlo Tree Search. (arXiv:2309.08611v1 [cs.AI]) Maneuver decision-making can be regarded as a Markov decision process and can be address by reinforcement learning. However, original reinforcement learning algorithms can hardly solve the maneuvering decision-making problem. One reason is that agents use random actions in the early stages of traini...

Prompting Segmentation with Sound is Generalizable Audio-Visual Source Localizer. (arXiv:2309.07929v1 [cs.CV])

Prompting Segmentation with Sound is Generalizable Audio-Visual Source Localizer. (arXiv:2309.07929v1 [cs.CV]) Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve....

Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023. (arXiv:2309.07925v1 [eess.AS])

Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023. (arXiv:2309.07925v1 [eess.AS]) In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathe...

Falcon 180B foundation model from TII is now available via Amazon SageMaker JumpStart

Falcon 180B foundation model from TII is now available via Amazon SageMaker JumpStart Today, we are excited to announce that the Falcon 180B foundation model developed by Technology Innovation Institute (TII) is available for customers through Amazon SageMaker JumpStart to deploy with one-click for running inference. With a 180-billion-parameter size and trained on a massive 3.5-tril...

DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs. (arXiv:2309.03907v1 [q-bio.BM])

DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs. (arXiv:2309.03907v1 [q-bio.BM]) A ChatGPT-like system for drug compounds could be a game-changer in pharmaceutical research, accelerating drug discovery, enhancing our understanding of structure-activity relationships, guiding lead optimization, aiding drug repurposing, reducing the failure rate, and streamlining clinical trials.....

Weakly supervised learning for pattern classification in serial femtosecond crystallography. (arXiv:2309.04474v1 [cond-mat.mtrl-sci])

Weakly supervised learning for pattern classification in serial femtosecond crystallography. (arXiv:2309.04474v1 [cond-mat.mtrl-sci]) Serial femtosecond crystallography at X-ray free electron laser facilities opens a new era for the determination of crystal structure. However, the data processing of those experiments is facing unprecedented challenge, because the total number of diffraction patterns needed to determinate a high-re...

tSPM+; a high-performance algorithm for mining transitive sequential patterns from clinical data. (arXiv:2309.05671v1 [cs.LG])

tSPM+; a high-performance algorithm for mining transitive sequential patterns from clinical data. (arXiv:2309.05671v1 [cs.LG]) The increasing availability of large clinical datasets collected from patients can enable new avenues for computational characterization of complex diseases using different analytic algorithms. One of the promising new methods for extracting knowledge from large clinical datasets involves temporal p...

Using wearable device-based machine learning models to autonomously identify older adults with poor cognition. (arXiv:2309.07133v1 [eess.SP])

Using wearable device-based machine learning models to autonomously identify older adults with poor cognition. (arXiv:2309.07133v1 [eess.SP]) Conducting cognitive tests is time-consuming for patients and clinicians. Wearable device-based prediction models allow for continuous health monitoring under normal living conditions and could offer an alternative to identifying older adults with cognitive impairments for early interventions. In th...

Ontologies for increasing the FAIRness of plant research data. (arXiv:2309.07129v1 [cs.DL])

Ontologies for increasing the FAIRness of plant research data. (arXiv:2309.07129v1 [cs.DL]) The importance of improving the FAIRness (findability, accessibility, interoperability, reusability) of research data is undeniable, especially in the face of large, complex datasets currently being produced by omics technologies. Facilitating the integration of a dataset with other types of data in...

Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection. (arXiv:2309.06449v1 [cond-mat.mes-hall])

Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection. (arXiv:2309.06449v1 [cond-mat.mes-hall]) In the autoencoder based anomaly detection paradigm, implementing the autoencoder in edge devices capable of learning in real-time is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these limitations can be addressed by designing an autoencoder with...

AGIBench: A Multi-granularity, Multimodal, Human-referenced, Auto-scoring Benchmark for Large Language Models. (arXiv:2309.06495v1 [cs.CL])

AGIBench: A Multi-granularity, Multimodal, Human-referenced, Auto-scoring Benchmark for Large Language Models. (arXiv:2309.06495v1 [cs.CL]) Large language models (LLMs) like ChatGPT have revealed amazing intelligence. How to evaluate the question-solving abilities of LLMs and their degrees of intelligence is a hot-spot but challenging issue. First, the question-solving abilities are interlaced with different ability branches like unders...

Studying the impacts of pre-training using ChatGPT-generated text on downstream tasks. (arXiv:2309.05668v1 [cs.CL])

Studying the impacts of pre-training using ChatGPT-generated text on downstream tasks. (arXiv:2309.05668v1 [cs.CL]) In recent times, significant advancements have been witnessed in the field of language models, particularly with the emergence of Large Language Models (LLMs) that are trained on vast amounts of data extracted from internet archives. These LLMs, such as ChatGPT, have become widely accessible, allowi...

Amazon SageMaker simplifies the Amazon SageMaker Studio setup for individual users

Amazon SageMaker simplifies the Amazon SageMaker Studio setup for individual users Today, we are excited to announce the simplified Quick setup experience in Amazon SageMaker. With this new capability, individual users can launch Amazon SageMaker Studio with default presets in minutes. SageMaker Studio is an integrated development environment (IDE) for machine learning (ML). ML pr...

Multimodal machine learning for materials science: composition-structure bimodal learning for experimentally measured properties. (arXiv:2309.04478v1 [cond-mat.mtrl-sci])

Multimodal machine learning for materials science: composition-structure bimodal learning for experimentally measured properties. (arXiv:2309.04478v1 [cond-mat.mtrl-sci]) The widespread application of multimodal machine learning models like GPT-4 has revolutionized various research fields including computer vision and natural language processing. However, its implementation in materials informatics remains underexplored, despite the presence of materials data across....

A recommender for the management of chronic pain in patients undergoing spinal cord stimulation. (arXiv:2309.03918v1 [cs.AI])

A recommender for the management of chronic pain in patients undergoing spinal cord stimulation. (arXiv:2309.03918v1 [cs.AI]) Spinal cord stimulation (SCS) is a therapeutic approach used for the management of chronic pain. It involves the delivery of electrical impulses to the spinal cord via an implanted device, which when given suitable stimulus parameters can mask or block pain signals. Selection of optimal stimulation....

Best practices and design patterns for building machine learning workflows with Amazon SageMaker Pipelines

Best practices and design patterns for building machine learning workflows with Amazon SageMaker Pipelines Amazon SageMaker Pipelines is a fully managed AWS service for building and orchestrating machine learning (ML) workflows. SageMaker Pipelines offers ML application developers the ability to orchestrate different steps of the ML workflow, including data loading, data transformation, training, tuning,...

Demystifying the Physics of Deep Learning

Demystifying the Physics of Deep Learning Deep learning, a subset of artificial intelligence (AI), has been a subject of immense interest and research in recent years due to its potential to revolutionize various industries. However, the underlying physics of deep learning remains a complex and often misunderstood area. This article aims to...

Evaluation of Reinforcement Learning Techniques for Trading on a Diverse Portfolio. (arXiv:2309.03202v1 [q-fin.TR])

Evaluation of Reinforcement Learning Techniques for Trading on a Diverse Portfolio. (arXiv:2309.03202v1 [q-fin.TR]) This work seeks to answer key research questions regarding the viability of reinforcement learning over the S&P 500 index. The on-policy techniques of Value Iteration (VI) and State-action-reward-state-action (SARSA) are implemented along with the off-policy technique of Q-Learning. The models are t...

Pioneers in Machine Learning: Voices that Shape the Field

Pioneers in Machine Learning: Voices that Shape the Field The field of machine learning has made tremendous progress over the past few decades, largely due to the pioneering efforts of a small group of scientists, researchers, and innovators. Their work has led to some of the most significant advancements in technology, and their voices continue to shape t...

Improving asset health and grid resilience using machine learning

Improving asset health and grid resilience using machine learning This post is co-written with Travis Bronson, and Brian L Wilkerson from Duke Energy Machine learning (ML) is transforming every industry, process, and business, but the path to success is not always straightforward. In this blog post, we demonstrate how Duke Energy, a Fortune 150 company headquarter...

The Potential of Machine Learning in Climate Change Predictions

The Potential of Machine Learning in Climate Change Predictions Climate change is an urgent global issue that requires immediate attention and action. It has a profound influence on the natural world and human life, threatening agricultural productivity, water supply, and even the existence of some species. Predicting the impacts of climate change is therefore a...

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design. (arXiv:2309.03208v1 [cs.AR])

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design. (arXiv:2309.03208v1 [cs.AR]) Logic Synthesis (LS) plays a vital role in chip design — a cornerstone of the semiconductor industry. A key task in LS is to transform circuits — modeled by directed acyclic graphs (DAGs) — into simplified circuits with equivalent functionalities. To tackle this task, many LS operators apply t...

Enable pod-based GPU metrics in Amazon CloudWatch

Enable pod-based GPU metrics in Amazon CloudWatch In February 2022, Amazon Web Services added support for NVIDIA GPU metrics in Amazon CloudWatch, making it possible to push metrics from the Amazon CloudWatch Agent to Amazon CloudWatch and monitor your code for optimal GPU utilization. Since then, this feature has been integrated into many of our m...

Observe Locally, Classify Globally: Using GNNs to Identify Sparse Matrix Structure. (arXiv:2309.02442v1 [math.NA])

Observe Locally, Classify Globally: Using GNNs to Identify Sparse Matrix Structure. (arXiv:2309.02442v1 [math.NA]) The performance of sparse matrix computation highly depends on the matching of the matrix format with the underlying structure of the data being computed on. Different sparse matrix formats are suitable for different structures of data. Therefore, the first challenge is identifying the matrix struct...

Run multiple generative AI models on GPU using Amazon SageMaker multi-model endpoints with TorchServe and save up to 75% in inference costs

Run multiple generative AI models on GPU using Amazon SageMaker multi-model endpoints with TorchServe and save up to 75% in inference costs Multi-model endpoints (MMEs) are a powerful feature of Amazon SageMaker designed to simplify the deployment and operation of machine learning (ML) models. With MMEs, you can host multiple models on a single serving container and host all the models behind a single endpoint. The SageMaker platform au...

Through their eyes: multi-subject Brain Decoding with simple alignment techniques. (arXiv:2309.00627v1 [q-bio.NC])

Through their eyes: multi-subject Brain Decoding with simple alignment techniques. (arXiv:2309.00627v1 [q-bio.NC]) Previous brain decoding research primarily involves single-subject studies, reconstructing stimuli via fMRI activity from the same subject. Our study aims to introduce a generalization technique for cross-subject brain decoding, facilitated by exploring data alignment methods. We utilized the NSD da...

Optimize deployment cost of Amazon SageMaker JumpStart foundation models with Amazon SageMaker asynchronous endpoints

Optimize deployment cost of Amazon SageMaker JumpStart foundation models with Amazon SageMaker asynchronous endpoints The success of generative AI applications across a wide range of industries has attracted the attention and interest of companies worldwide who are looking to reproduce and surpass the achievements of competitors or solve new and exciting use cases. These customers are looking into foundation models...

Advent of Machine Learning in Agriculture: Innovating for a Green Future

Advent of Machine Learning in Agriculture: Innovating for a Green Future The advent of machine learning in the field of agriculture marks a significant turning point in how we approach farming and food production. It is a technological revolution that is innovating for a green future, leveraging artificial intelligence and data analysis to optimize agricultural practices...

High Spectral Spatial Resolution Synthetic HyperSpectral Dataset form multi-source fusion. (arXiv:2309.00005v1 [cs.CV])

High Spectral Spatial Resolution Synthetic HyperSpectral Dataset form multi-source fusion. (arXiv:2309.00005v1 [cs.CV]) This research paper introduces a synthetic hyperspectral dataset that combines high spectral and spatial resolution imaging to achieve a comprehensive, accurate, and detailed representation of observed scenes or objects. Obtaining such desirable qualities is challenging when relying on a single came...

Unsupervised discovery of Interpretable Visual Concepts. (arXiv:2309.00018v1 [cs.CV])

Unsupervised discovery of Interpretable Visual Concepts. (arXiv:2309.00018v1 [cs.CV]) Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a visualization technique containing a high level of information, but....

Elevating the generative AI experience: Introducing streaming support in Amazon SageMaker hosting

Elevating the generative AI experience: Introducing streaming support in Amazon SageMaker hosting We’re excited to announce the availability of response streaming through Amazon SageMaker real-time inference. Now you can continuously stream inference responses back to the client when using SageMaker real-time inference to help you build interactive experiences for generative AI applications su...

Machine Learning and Big Data: A Match Made in Heaven

Machine Learning and Big Data: A Match Made in Heaven Machine learning and big data are two of the most significant technological trends of our time, and they share a profound symbiotic relationship. The technological era has witnessed the rapid growth of data from various sources, including social media, internet-connected devices, and business proces...

This demo tests your understanding of light | Barber pole, part 1

This demo tests your understanding of light | Barber pole, part 1 Optical rotation, but with a twist Next video: https://youtu.be/aXRTczANuIs Steve Mould’d video on the topic: https://youtu.be/975r9a7FMqc Help fund future projects: https://www.patreon.com/3blue1brown An equally valuable form of support is to simply share the videos. Thanks to Quinn Brodsky for s...

How Machine Learning is Transforming Customer Service in the Digital Age

How Machine Learning is Transforming Customer Service in the Digital Age In an era where digitalization is rapidly evolving, machine learning has become an instrumental tool in transforming various industries, including customer service. The integration of machine learning technology not only enhances the quality of customer service but also significantly improves effici...

The origin of light, scattering, and polarization | Barber pole, part 2

The origin of light, scattering, and polarization | Barber pole, part 2 Explaining the barber pole effect from the last video: https://youtu.be/QCX62YJCmGk Help fund future projects: https://www.patreon.com/3blue1brown An equally valuable form of support is to simply share the videos. Timestamps: 0:00 – Recap 0:44 – The radiation law 6:10 – Simulating the radiatio...

Learning Collaborative Information Dissemination with Graph-based Multi-Agent Reinforcement Learning. (arXiv:2308.16198v1 [cs.LG])

Learning Collaborative Information Dissemination with Graph-based Multi-Agent Reinforcement Learning. (arXiv:2308.16198v1 [cs.LG]) In modern communication systems, efficient and reliable information dissemination is crucial for supporting critical operations across domains like disaster response, autonomous vehicles, and sensor networks. This paper introduces a Multi-Agent Reinforcement Learning (MARL) approach as a significant...

Use Amazon SageMaker Model Card sharing to improve model governance

Use Amazon SageMaker Model Card sharing to improve model governance As Artificial Intelligence (AI) and Machine Learning (ML) technologies have become mainstream, many enterprises have been successful in building critical business applications powered by ML models at scale in production. However, since these ML models are making critical business decisions for the b...

Online Job Failure Prediction in an HPC System. (arXiv:2308.15481v1 [cs.DC])

Online Job Failure Prediction in an HPC System. (arXiv:2308.15481v1 [cs.DC]) Modern High Performance Computing (HPC) systems are complex machines, with major impacts on economy and society. Along with their computational capability, their energy consumption is also steadily raising, representing a critical issue given the ongoing environmental and energetic crisis. Therefore...

Deploy self-service question answering with the QnABot on AWS solution powered by Amazon Lex with Amazon Kendra and large language models

Deploy self-service question answering with the QnABot on AWS solution powered by Amazon Lex with Amazon Kendra and large language models Powered by Amazon Lex, the QnABot on AWS solution is an open-source, multi-channel, multi-language conversational chatbot. QnABot allows you to quickly deploy self-service conversational AI into your contact center, websites, and social media channels, reducing costs, shortening hold times, and impr...