Directions in Hybrid Intelligence: Complementing AI Systems with Human Intelligence

Authors: Ece Kamar

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Evaluations of the Crowd Synth effort on Galaxy Zoo demonstrate that significant gains can be achieved from the optimization of access to human intelligence. The experiments show that Crowd Synth can achieve the maximum accuracy of the original system by hiring only 47% of the workers who participated in the open world run of the system.
Researcher Affiliation Industry Ece Kamar Microsoft Research eckamar@microsoft.com
Pseudocode No The paper describes algorithms like 'MC-VOI' but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodologies described.
Open Datasets Yes It uses Galaxy Zoo, a citizen science project that seeks volunteers input to classify images of millions of celestial objects, as a testbed for studies.
Dataset Splits No The paper mentions the datasets used (e.g., Galaxy Zoo, Planet Hunters) but does not provide specific details on training, validation, or test splits (e.g., percentages, sample counts, or citations to predefined splits).
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory, or processor types) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies, libraries, or solver names with version numbers.
Experiment Setup No The paper discusses concepts like 'decision-making problem as a Partially Observable Markov Decision Process' and 'Monte-Carlo planning algorithm', but it does not include specific experimental setup details such as hyperparameter values, training configurations, or system-level settings.