I Don’t Know – Prediction Cascades Framework
Advances in deep learning have led to substantial increases in prediction accuracy as well as the cost of rendering predictions. We conjecture that for a majority of real-world inputs, the recent advances in deep learning have created models that effectively ‘over-think’ on simple inputs. In this paper we revisit the classic idea of prediction cascades to reduce prediction costs. We introduce the ‘I Don’t Know’ (IDK) prediction cascades framework, a general framework for constructing prediction cascades for arbitrary multi-class prediction tasks. We propose two baseline methods for constructing cascades as well as a new objective within this framework and evaluate these techniques on a range of benchmark and real-world datasets to demonstrate the prediction cascades can achieve 1.7-10.5x speedups in image classification tasks while maintaining comparable accuracy to state-of-the-art models. When combined with human experts, prediction cascades can achieve nearly perfect accuracy(within 5%) while requiring human intervention on less than 30% of the queries. …

Preferential Attachment (PA)
A preferential attachment process is any of a class of processes in which some quantity, typically some form of wealth or credit, is distributed among a number of individuals or objects according to how much they already have, so that those who are already wealthy receive more than those who are not. ‘Preferential attachment’ is only the most recent of many names that have been given to such processes. They are also referred to under the names ‘Yule process’, ‘cumulative advantage’, ‘the rich get richer’, and, less correctly, the ‘Matthew effect’. They are also related to Gibrat’s law. The principal reason for scientific interest in preferential attachment is that it can, under suitable circumstances, generate power law distributions. …

Multi Agent System (MAS)
A multi-agent system (M.A.S.) is a computerized system composed of multiple interacting intelligent agents within an environment. Multi-agent systems can be used to solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include some methodic, functional, procedural approach, algorithmic search or reinforcement learning. Although there is considerable overlap, a multi-agent system is not always the same as an agent-based model (ABM). The goal of an ABM is to search for explanatory insight into the collective behavior of agents (which don’t necessarily need to be “intelligent”) obeying simple rules, typically in natural systems, rather than in solving specific practical or engineering problems. The terminology of ABM tends to be used more often in the sciences, and MAS in engineering and technology. Topics where multi-agent systems research may deliver an appropriate approach include online trading, disaster response, and modelling social structures. …