اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWidening Access to Applied Machine Learning with TinyML
78
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Broadening access to both computational and educational resources is critical to diffusing machine-learning (ML) innovation. However, today, most ML resources and experts are siloed in a few countries and organizations. In this paper, we describe our pedagogical approach to increasing access to applied ML through a massive open online course (MOOC) on Tiny Machine Learning (TinyML). We suggest that TinyML, ML on resource-constrained embedded devices, is an attractive means to widen access because TinyML both leverages low-cost and globally accessible hardware, and encourages the development of complete, self-contained applications, from data collection to deployment. To this end, a collaboration between academia (Harvard University) and industry (Google) produced a four-part MOOC that provides application-oriented instruction on how to develop solutions using TinyML. The series is openly available on the edX MOOC platform, has no prerequisites beyond basic programming, and is designed for learners from a global variety of backgrounds. It introduces pupils to real-world applications, ML algorithms, data-set engineering, and the ethical considerations of these technologies via hands-on programming and deployment of TinyML applications in both the cloud and their own microcontrollers. To facilitate continued learning, community building, and collaboration beyond the courses, we launched a standalone website, a forum, a chat, and an optional course-project competition. We also released the course materials publicly, hoping they will inspire the next generation of ML practitioners and educators and further broaden access to cutting-edge ML technologies.
قيم البحث
اقرأ أيضاً
Deep learning inference on embedded devices is a burgeoning field with myriad applications because tiny embedded devices are omnipresent. But we must overcome major challenges before we can benefit from this opportunity. Embedded processors are sever
ely resource constrained. Their nearest mobile counterparts exhibit at least a 100 -- 1,000x difference in compute capability, memory availability, and power consumption. As a result, the machine-learning (ML) models and associated ML inference framework must not only execute efficiently but also operate in a few kilobytes of memory. Also, the embedded devices ecosystem is heavily fragmented. To maximize efficiency, system vendors often omit many features that commonly appear in mainstream systems, including dynamic memory allocation and virtual memory, that allow for cross-platform interoperability. The hardware comes in many flavors (e.g., instruction-set architecture and FPU support, or lack thereof). We introduce TensorFlow Lite Micro (TF Micro), an open-source ML inference framework for running deep-learning models on embedded systems. TF Micro tackles the efficiency requirements imposed by embedded-system resource constraints and the fragmentation challenges that make cross-platform interoperability nearly impossible. The framework adopts a unique interpreter-based approach that provides flexibility while overcoming these challenges. This paper explains the design decisions behind TF Micro and describes its implementation details. Also, we present an evaluation to demonstrate its low resource requirement and minimal run-time performance overhead.
This paper proposes a methodology to estimate stress in the subsurface by a hybrid method combining finite element modeling and neural networks. This methodology exploits the idea of obtaining a multi-frequency solution in the numerical modeling of s
ystems whose behavior involves a wide span of length scales. One low-frequency solution is obtained via inexpensive finite element modeling at a coarse scale. The second solution provides the fine-grained details introduced by the heterogeneity of the free parameters at the fine scale. This high-frequency solution is estimated via neural networks -trained with partial solutions obtained in high-resolution finite-element models. When the coarse finite element solutions are combined with the neural network estimates, the results are within a 2% error of the results that would be computed with high-resolution finite element models. This paper discusses the benefits and drawbacks of the method and illustrates their applicability via a worked example.
We present recent results from the LCDM (Laboratory for Cosmological Data Mining; http://lcdm.astro.uiuc.edu) collaboration between UIUC Astronomy and NCSA to deploy supercomputing cluster resources and machine learning algorithms for the mining of t
erascale astronomical datasets. This is a novel application in the field of astronomy, because we are using such resources for data mining, and not just performing simulations. Via a modified implementation of the NCSA cyberenvironment Data-to-Knowledge, we are able to provide improved classifications for over 100 million stars and galaxies in the Sloan Digital Sky Survey, improved distance measures, and a full exploitation of the simple but powerful k-nearest neighbor algorithm. A driving principle of this work is that our methods should be extensible from current terascale datasets to upcoming petascale datasets and beyond. We discuss issues encountered to-date, and further issues for the transition to petascale. In particular, disk I/O will become a major limiting factor unless the necessary infrastructure is implemented.
153 -
Nicholas M. Ball
, Robert J. Brunner
, Adam D. Myers (University ofn Illinois at Urbana-Champaign
2007
We present recent results from the Laboratory for Cosmological Data Mining (http://lcdm.astro.uiuc.edu) at the National Center for Supercomputing Applications (NCSA) to provide robust classifications and photometric redshifts for objects in the teras
cale-class Sloan Digital Sky Survey (SDSS). Through a combination of machine learning in the form of decision trees, k-nearest neighbor, and genetic algorithms, the use of supercomputing resources at NCSA, and the cyberenvironment Data-to-Knowledge, we are able to provide improved classifications for over 100 million objects in the SDSS, improved photometric redshifts, and a full exploitation of the powerful k-nearest neighbor algorithm. This work is the first to apply the full power of these algorithms to contemporary terascale astronomical datasets, and the improvement over existing results is demonstrable. We discuss issues that we have encountered in dealing with data on the terascale, and possible solutions that can be implemented to deal with upcoming petascale datasets.
Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, c
ontrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
