منابع مشابه
When mind meets machine
into sufferers from amyotrophic lateral sclerosis (ALS) and brain-stem stroke, which enables them to move a computer cursor, albeit slowly. The device uses electrodes attached to amplifiers and FM transmitters transplanted 5 mm deep—just under the scalp—into the brain. The electrodes encourage brain tissue to grow around them, thus stabilizing them against any movement and resulting distortion ...
متن کاملWhen Machine Learning Meets AI and Game Theory
We study the problem of development of intelligent machine learning applications to exploit the problems of adaptation that arise in multi-agent systems, for expected-long-termprofit maximization. We present two results. First, we propose a learning algorithm for the Iterated Prisoners Dilemma (IPD) problem. Using numerical analysis we show that it performs strictly better than the tit-for-tat ...
متن کاملWhen Lempel-Ziv-Welch Meets Machine Learning: A Case Study of Accelerating Machine Learning using Coding
In this paper we study the use of coding techniques to accelerate machine learning (ML). Coding techniques, such as prefix codes, have been extensively studied and used to accelerate low-level data processing primitives such as scans in a relational database system. However, there is little work on how to exploit them to accelerate ML algorithms. In fact, applying coding techniques for faster M...
متن کاملStratified Sampling Meets Machine Learning
This paper solves a specialized regression problem to obtain sampling probabilities for records in databases. The goal is to sample a small set of records over which evaluating aggregate queries can be done both efficiently and accurately. We provide a principled and provable solution for this problem; it is parameterless and requires no data insights. Unlike standard regression problems, the l...
متن کاملWhen Semi-supervised Learning Meets Ensemble Learning
Semi-supervised learning and ensemble learning are two important machine learning paradigms. The former attempts to achieve strong generalization by exploiting unlabeled data; the latter attempts to achieve strong generalization by using multiple learners. Although both paradigms have achieved great success during the past decade, they were almost developed separately. In this paper, we advocat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Data and Information Management
سال: 2017
ISSN: 2543-9251
DOI: 10.1515/dim-2017-0012