Related papers: Lessons from the Coinseminar
In this paper we analyze the communication network of 50 students from five universities in three countries participating in a joint course on Collaborative Innovation Networks (COINs). Students formed ten teams. Interaction variables…
The 5th annual international conference on Collaborative Innovation Networks Conference (COINS) takes place at Keio University from March 12 to 14, 2015. COINS15 brings together practitioners, researchers and students of the emerging…
Where science, design, business and art meet, COINs13 looks at the emerging forces behind the phenomena of open-source, creative, entrepreneurial and social movements. COINs13 combines a wide range of interdisciplinary fields such as social…
This study aims to investigate the COINs concept of rotating leadership within a Knowledge Building context. Individual and group level leadership patterns in a grade 4 science class were explored through temporal visualization of…
In this paper we consider online distributed learning problems. Online distributed learning refers to the process of training learning models on distributed data sources. In our setting a set of agents need to cooperatively train a learning…
A COllective INtelligence (COIN) is a set of interacting reinforcement learning (RL) algorithms designed in an automated fashion so that their collective behavior optimizes a global utility function. We summarize the theory of COINs, then…
Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the…
Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the…
In this paper we provide an account of how we ported a text and data mining course online in summer 2020 as a result of the COVID-19 pandemic and how we improved it in a second pilot run. We describe the course, how we adapted it over the…
Machine learning models have achieved, and in some cases surpassed, human-level performance in various tasks, mainly through centralized training of static models and the use of large models stored in centralized clouds for inference.…
There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and…
Recently, the academic community has been giving much attention to Cooperative Learning System, a group learning method combined with pedagogy and social psychology. It allows group members to gain knowledge through collaborations and…
Motivated by the problem of tracking a direction in a decentralized way, we consider the general problem of cooperative learning in multi-agent systems with time-varying connectivity and intermittent measurements. We propose a distributed…
We report our experience in two installations of a course on data visualization that featured project-based learning. Given the rationale of this approach, we show which input was provided when necessary for the students to achieve their…
As the complexity of our neural network models grow, so too do the data and computation requirements for successful training. One proposed solution to this problem is training on a distributed network of computational devices, thus…
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee…
Virtual learning environments are actual solutions that facilitate collaborative learning, both in classroom and distance education. However, such environments are not yet fully disseminated in Brazilian universities. This work reports a…
Bipartite graphs are powerful data structures to model interactions between two types of nodes, which have been used in a variety of applications, such as recommender systems, information retrieval, and drug discovery. A fundamental…
The virtual meeting was a success. Several people told us that this was "the best virtual meeting they had seen so far", which, a year into the pandemic and without a commercial provider in the back, is a great success. The biggest point of…
Network testing plays an important role in the iterative process of developing new communication protocols and algorithms. However, test environments have to keep up with the evolution of technology and require continuous update and…