With the increased sophistication of AI techniques, the application of these systems has been expanding to ever newer fields. Increasingly, these systems are being used in modeling of human aesthetics and creativity, e.g. how humans create artworks and design products. Our lab has developed one such AI creativity deep learning system that can be used to create artworks in the form of images and videos. In this paper, we describe this system and its use in studying the human visual system and the formation of aesthetic experiences. Specifically, we show how time-based AI created media can be used to explore the nature of the dual-pathway neuro-architecture of the human visual system and how this relates to higher cognitive judgments such as aesthetic experiences that rely on these divergent information streams. We propose a theoretical framework for how the movement within percepts such as video clips, causes the engagement of reflexive attention and a subsequent focus on visual information that are primarily processed via the dorsal stream, thereby modulating aesthetic experiences that rely on information relayed via the ventral stream. We outline our recent study in support of our proposed framework, which serves as the first study that investigates the relationship between the two visual streams and aesthetic experiences.

Saudi authorities attempt to control a fire at an Aramco factory. The world's largest oil processing facility and a nearby oil field in Saudi Arabia were set ablaze early Saturday morning after reported drone attacks by Iranian-backed Yemeni rebels. The Interior Ministry was quoted by state-run media as saying the fires at the Abqaiq oil processing facility in Buqyaq and the nearby Khurais oil field operated by Saudi Aramco were "targeted by drones." It wasn't immediately clear if there were any injuries, nor what effect it would have on oil production in the kingdom. Smoke is seen following a fire at Aramco facility in the eastern city of Abqaiq, Saudi Arabia, September 14, 2019.

DUBAI, UNITED ARAB EMIRATES – Drones attacked the world's largest oil processing facility in Saudi Arabia and a major oil field operated by Saudi Aramco early Saturday, the kingdom's Interior Ministry said, sparking a huge fire at a processor crucial to global energy supplies. No one immediately claimed responsibility for the attacks in Buqyaq and the Khurais oil field, though Yemen's Houthi rebels previously launched drone assaults deep inside of the kingdom. It wasn't clear if there were any injuries in the attacks, nor what effect it would have on oil production in the kingdom. The attack also likely will heighten tensions further across the wider Persian Gulf amid a confrontation between the U.S. and Iran over its unraveling nuclear deal with world powers. Online videos apparently shot in Buqyaq included the sound of gunfire in the background.

Traditional control methods are inadequate in many deployment settings involving control of Cyber-Physical Systems (CPS). In such settings, CPS controllers must operate and respond to unpredictable interactions, conditions, or failure modes. Dealing with such unpredictability requires the use of executive and cognitive control functions that allow for planning and reasoning. Motivated by the sport of drone racing, this dissertation addresses these concerns for state-of-the-art flight control by investigating the use of deep neural networks to bring essential elements of higher-level cognition for constructing low level flight controllers. This thesis reports on the development and release of an open source, full solution stack for building neuro-flight controllers. This stack consists of the methodology for constructing a multicopter digital twin for synthesize the flight controller unique to a specific aircraft, a tuning framework for implementing training environments (GymFC), and a firmware for the world's first neural network supported flight controller (Neuroflight). GymFC's novel approach fuses together the digital twinning paradigm for flight control training to provide seamless transfer to hardware. Additionally, this thesis examines alternative reward system functions as well as changes to the software environment to bridge the gap between the simulation and real world deployment environments. Work summarized in this thesis demonstrates that reinforcement learning is able to be leveraged for training neural network controllers capable, not only of maintaining stable flight, but also precision aerobatic maneuvers in real world settings. As such, this work provides a foundation for developing the next generation of flight control systems.

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we introduce a formal definition of robustness which can be viewed as a localized Lipschitz constant of the network function, quantified in the domain of the data to be classified. We compare this notion of robustness to existing ones, and study its connections with methods in the literature. We evaluate this metric by performing experiments on various competitive vision datasets.

The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computational resources, but also embedding biases and enabling unintended negative uses. In this paper, we treat pretrained models as objects of study and discuss the ethical impacts of their sociological position. We discuss how pretrained models are developed and compared under the common task framework, but that this may make self-regulation inadequate. Further how pretrained models may have a performative effect on society that exacerbates biases. We then discuss how pretrained models move through actor networks as a kind of computationally immutable mobile, but that users also act as agents of technological change by reinterpreting them via fine-tuning and transfer. We further discuss how users may use pretrained models in malicious ways, drawing a novel connection between the responsible innovation and user-centered innovation literatures. We close by discussing how this sociological understanding of pretrained models can inform AI governance frameworks for fairness, accountability, and transparency.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Bushfires pose a significant threat to Australia's regional areas. To minimise risk and increase resilience, communities need robust evacuation strategies that account for people's likely behaviour both before and during a bushfire. Agent-based modelling (ABM) offers a practical way to simulate a range of bushfire evacuation scenarios. However, the ABM should reflect the diversity of possible human responses in a given community. The Belief-Desire-Intention (BDI) cognitive model captures behaviour in a compact representation that is understandable by domain experts. Within a BDI-ABM simulation, individual BDI agents can be assigned profiles that determine their likely behaviour. Over a population of agents their collective behaviour will characterise the community response. These profiles are drawn from existing human behaviour research and consultation with emergency services personnel and capture the expected behaviours of identified groups in the population, both prior to and during an evacuation. A realistic representation of each community can then be formed, and evacuation scenarios within the simulation can be used to explore the possible impact of population structure on outcomes. It is hoped that this will give an improved understanding of the risks associated with evacuation, and lead to tailored evacuation plans for each community to help them prepare for and respond to bushfire.

A neural architecture, which is the structure and connectivity of the network, is typically either hand-crafted or searched by optimizing some specific objective criterion (e.g., classification accuracy). Since the space of all neural architectures is huge, search methods are usually heuristic and do not guarantee finding the optimal architecture, with respect to the objective criterion. In addition, these search methods might require a large number of supervised training iterations and use a high amount of computational resources, rendering the solution infeasible for many applications. Moreover, optimizing for a specific criterion might result in a model that is suboptimal for other useful criteria such as model size, representation of uncertainty and robustness to adversarial attacks. Thus, the resulting architectures of most strategies used today, whether hand crafting or heuristic searches, are densely connected networks, which are not an optimal solution for the objective they were created to achieve, let alone other objectives.

As it is, the world is unfair. The question now is, do we want automated tech to be unfair too? As we build more and more AI-dependent smart digital infrastructure in our cities and beyond, we have pretty much overlooked the emerging character of artificial intelligence that would have a profound bearing on our nature and future. Are we happy with algorithms making decisions for us? Naturally, one would expect the algorithm to possess discretion.