Resource-constrained deep learning: challenges and practices
نویسندگان
چکیده
منابع مشابه
Challenges in Deep Learning
In recent years, Deep Learning methods and architectures have reached impressive results, allowing quantum-leap improvements in performance in many difficult tasks, such as speech recognition, end-toend machine translation, image classification/understanding, just to name a few. After a brief introduction to some of the main achievements of Deep Learning, we discuss what we think are the genera...
متن کاملCommunity-Based Learning: Practices, Challenges, and Reflections
This paper will highlight an innovate practice in teaching and learning by reflecting on two fourthyear sociology seminar classes that participated in a community-based learning project at York University. Fifty students collaborated in three to six person teams to work on a problem/issue identified by one of five not-for-profit organizations who work with and/or for women as victims, offenders...
متن کاملThe Scope and Challenges for Deep Learning.
I’ve been using machine-learning methods for more than two decades for a variety of problems, the most challenging of which has been to design a set of algorithms that learn from data how to trade securities profitably on their own and with minimal human input. I started this research to answer a basic question, namely, whether machine-learning algorithms could be shaped to make investment deci...
متن کاملResource Constrained Exploration in Reinforcement Learning
This paper examines temporal difference reinforcement learning (RL) with adaptive and directed exploration for resource-limited missions. The scenario considered is for an energy-limited agent which must explore an unknown region to find new energy sources. The presented algorithm uses a Gaussian Process (GP) regression model to estimate the value function in an RL framework. However, to avoid ...
متن کاملTwo-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices
With the rapid proliferation of Internet of Things and intelligent edge devices, there is an increasing need for implementing machine learning algorithms, including deep learning, on resource-constrained mobile embedded devices with limited memory and computation power. Typical large Convolutional Neural Networks (CNNs) need large amounts of memory and computational power, and cannot be deploye...
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: SCIENTIA SINICA Informationis
سال: 2018
ISSN: 1674-7267
DOI: 10.1360/n112017-00216