Collaborating Authors

Neural networks as the architecture of human work – Esko Kilpi – Medium


In the brain there are neurons that link. This firing together creates a connection. On the Internet there are servers and people that are linked in temporal interaction, sometimes as a result of being interested in the same topic, thus creating contextual interdependence. This short-term communication, firing together, sometimes leads to a longer-term relationship that increases the strength of the connection. So all interaction is always "local" creating "events", whether in the brain, in an organization, or on the Internet.

Novel Mechanisms for Natural Human-Robot Interactions in the DIARC Architecture

AAAI Conferences

Natural human-like human-robot interactions require many functional capabilities from a robot that have to be reflected in architectural components in the robotic control architecture.  In particular, various mechanisms for producing social behaviors , goal-oriented cognition , and robust intelligence are required.  In this paper, we present an overview of the most recent version of our DIARC architecture and show how several novel algorithms attempt to address these three areas, leading to more natural interactions with humans, while also extending the overall capability of the integrated system.

'Astrocyte' explores how architecture can interact with humans


Philip Beesley's Astrocyte aims to show that architecture can be more than just ornamental. Built from acrylic, mylar, sensors, custom glasswork, 3D-printed lights and using AI, chemistry and a responsive soundscape, it not only invokes emotional reactions but reacts to participants' movements and gestures. The giant, delicate-looking structure (inspired by astrocyte nerve cells), also prompts unusually respectful interactions from human observers.

AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction Machine Learning

Learning effective feature interactions is crucial for click-through rate (CTR) prediction tasks in recommender systems. In most of the existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all feature interactions brings large memory and computation cost. Even worse, useless interactions may introduce unnecessary noise and complicate the training process. In this work, we propose a two-stage algorithm called Automatic Feature Interaction Selection (AutoFIS). AutoFIS can automatically identify all the important feature interactions for factorization models with just the computational cost equivalent to training the target model to convergence. In the \emph{search stage}, instead of searching over a discrete set of candidate feature interactions, we relax the choices to be continuous by introducing the architecture parameters. By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model. In the \emph{re-train stage}, we keep the architecture parameters serving as an attention unit to further boost the performance. Offline experiments on three large-scale datasets (two public benchmarks, one private) demonstrate that the proposed AutoFIS can significantly improve various FM based models. AutoFIS has been deployed onto the training platform of Huawei App Store recommendation service, where a 10-day online A/B test demonstrated that AutoFIS improved the DeepFM model by 20.3\% and 20.1\% in terms of CTR and CVR respectively.

Explaining Local, Global, And Higher-Order Interactions In Deep Learning Artificial Intelligence

We present a simple yet highly generalizable method for explaining interacting parts within a neural network's reasoning process. In this work, we consider local, global, and higher-order statistical interactions. Generally speaking, local interactions occur between features within individual datapoints, while global interactions come in the form of universal features across the whole dataset. With deep learning, combined with some heuristics for tractability, we achieve state of the art measurement of global statistical interaction effects, including at higher orders (3-way interactions or more). We generalize this to the multidimensional setting to explain local interactions in multi-object detection and relational reasoning using the COCO annotated-image and Sort-Of-CLEVR toy datasets respectively. Here, we submit a new task for testing feature vector interactions, conduct a human study, propose a novel metric for relational reasoning, and use our interaction interpretations to innovate a more effective Relation Network. Finally, we apply these techniques on a real-world biomedical dataset to discover the higher-order interactions underlying Parkinson's disease clinical progression.