A Large-Scale Neural Network Which Recognizes Handwritten Kanji Characters

Neural Information Processing Systems

We propose a new way to construct a large-scale neural network for 3.000 handwritten Kanji characters recognition. This neural network consists of 3 parts: a collection of small-scale networks which are trained individually on a small number of Kanji characters; a network which integrates the output from the small-scale networks, and a process to facilitate the integration of these neworks. The recognition rate of the total system is comparable with those of the small-scale networks. Our results indicate that the proposed method is effective for constructing a large-scale network without loss of recognition performance.


Integrating Large-Scale Databases with Python

@machinelearnbot

This whitepaper covers details on integrating Python with commercial relational database management systems (RDBMS) including specifics on tools and resources to utilize.


Jordan's newest mall debuts large-scale green technology

U.S. News

In this July 4, 2016 photo, sunlight reflects on the glass exterior of Jordan's newest mall, the kingdom's first energy-efficient shopping complex in Amman, Jordan. In Abdali Mall, high-end boutiques, cinemas and gourmet coffee shops are tucked into an intricate ecosystem of natural heating and cooling, water recycling and hundreds of solar panels soaking up the sun's rays.


From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

#artificialintelligence

A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula,, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed.


From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

#artificialintelligence

A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula,, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed.