Collaborating Authors Artificial Intelligence

Computational Mechanism for the Effect of Psychosis Community Treatment: A Conceptual Review from Neurobiology to Social Interaction Artificial Intelligence

The computational underpinnings of positive psychotic symptoms have recently received significant attention. Candidate mechanisms include some combination of maladaptive priors and reduced updating of these priors during perception. A potential benefit of models with such mechanisms is their ability to link multiple levels of explanation. This is key to improving how we understand the experience of psychosis. Moreover, it points us towards more comprehensive avenues for therapeutic research by providing a putative mechanism that could allow for the generation of new treatments from first principles. In order to demonstrate this, our conceptual paper will discuss the application of the insights from previous computational models to an important and complex set of evidence-based clinical interventions with strong social elements, such as coordinated specialty care clinics in early psychosis and assertive community treatment. These interventions may include but also go beyond psychopharmacology, providing, we argue, structure and predictability for patients experiencing psychosis. We develop the argument that this structure and predictability directly counteract the relatively low precision afforded to sensory information in psychosis, while also providing the patient more access to external cognitive resources in the form of providers and the structure of the programs themselves. We discuss how computational models explain the resulting reduction in symptoms, as well as the predictions these models make about potential responses of patients to modifications or to different variations of these interventions. We also link, via the framework of computational models, the experiences of patients and response to interventions to putative neurobiology.

Equality before the Law: Legal Judgment Consistency Analysis for Fairness Artificial Intelligence

In a legal system, judgment consistency is regarded as one of the most important manifestations of fairness. However, due to the complexity of factual elements that impact sentencing in real-world scenarios, few works have been done on quantitatively measuring judgment consistency towards real-world data. In this paper, we propose an evaluation metric for judgment inconsistency, Legal Inconsistency Coefficient (LInCo), which aims to evaluate inconsistency between data groups divided by specific features (e.g., gender, region, race). We propose to simulate judges from different groups with legal judgment prediction (LJP) models and measure the judicial inconsistency with the disagreement of the judgment results given by LJP models trained on different groups. Experimental results on the synthetic data verify the effectiveness of LInCo. We further employ LInCo to explore the inconsistency in real cases and come to the following observations: (1) Both regional and gender inconsistency exist in the legal system, but gender inconsistency is much less than regional inconsistency; (2) The level of regional inconsistency varies little across different time periods; (3) In general, judicial inconsistency is negatively correlated with the severity of the criminal charges. Besides, we use LInCo to evaluate the performance of several de-bias methods, such as adversarial learning, and find that these mechanisms can effectively help LJP models to avoid suffering from data bias.

On the Complexity of Learning Description Logic Ontologies Artificial Intelligence

Ontologies are a popular way of representing domain knowledge, in particular, knowledge in domains related to life sciences. (Semi-)automating the process of building an ontology has attracted researchers from different communities into a field called "Ontology Learning". We provide a formal specification of the exact and the probably approximately correct learning models from computational learning theory. Then, we recall from the literature complexity results for learning lightweight description logic (DL) ontologies in these models. Finally, we highlight other approaches proposed in the literature for learning DL ontologies.

Exploiting Class Similarity for Machine Learning with Confidence Labels and Projective Loss Functions Artificial Intelligence

Class labels used for machine learning are relatable to each other, with certain class labels being more similar to each other than others (e.g. images of cats and dogs are more similar to each other than those of cats and cars). Such similarity among classes is often the cause of poor model performance due to the models confusing between them. Current labeling techniques fail to explicitly capture such similarity information. In this paper, we instead exploit the similarity between classes by capturing the similarity information with our novel confidence labels. Confidence labels are probabilistic labels denoting the likelihood of similarity, or confusability, between the classes. Often even after models are trained to differentiate between classes in the feature space, the similar classes' latent space still remains clustered. We view this type of clustering as valuable information and exploit it with our novel projective loss functions. Our projective loss functions are designed to work with confidence labels with an ability to relax the loss penalty for errors that confuse similar classes. We use our approach to train neural networks with noisy labels, as we believe noisy labels are partly a result of confusability arising from class similarity. We show improved performance compared to the use of standard loss functions. We conduct a detailed analysis using the CIFAR-10 dataset and show our proposed methods' applicability to larger datasets, such as ImageNet and Food-101N.

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI Artificial Intelligence

We introduce a visually-guided and physics-driven task-and-motion planning benchmark, which we call the ThreeDWorld Transport Challenge. In this challenge, an embodied agent equipped with two 9-DOF articulated arms is spawned randomly in a simulated physical home environment. The agent is required to find a small set of objects scattered around the house, pick them up, and transport them to a desired final location. We also position containers around the house that can be used as tools to assist with transporting objects efficiently. To complete the task, an embodied agent must plan a sequence of actions to change the state of a large number of objects in the face of realistic physical constraints. We build this benchmark challenge using the ThreeDWorld simulation: a virtual 3D environment where all objects respond to physics, and where can be controlled using fully physics-driven navigation and interaction API. We evaluate several existing agents on this benchmark. Experimental results suggest that: 1) a pure RL model struggles on this challenge; 2) hierarchical planning-based agents can transport some objects but still far from solving this task. We anticipate that this benchmark will empower researchers to develop more intelligent physics-driven robots for the physical world.

AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting Artificial Intelligence

Predicting accurate future trajectories of multiple agents is essential for autonomous systems, but is challenging due to the complex agent interaction and the uncertainty in each agent's future behavior. Forecasting multi-agent trajectories requires modeling two key dimensions: (1) time dimension, where we model the influence of past agent states over future states; (2) social dimension, where we model how the state of each agent affects others. Most prior methods model these two dimensions separately; e.g., first using a temporal model to summarize features over time for each agent independently and then modeling the interaction of the summarized features with a social model. This approach is suboptimal since independent feature encoding over either the time or social dimension can result in a loss of information. Instead, we would prefer a method that allows an agent's state at one time to directly affect another agent's state at a future time. To this end, we propose a new Transformer, AgentFormer, that jointly models the time and social dimensions. The model leverages a sequence representation of multi-agent trajectories by flattening trajectory features across time and agents. Since standard attention operations disregard the agent identity of each element in the sequence, AgentFormer uses a novel agent-aware attention mechanism that preserves agent identities by attending to elements of the same agent differently than elements of other agents. Based on AgentFormer, we propose a stochastic multi-agent trajectory prediction model that can attend to features of any agent at any previous timestep when inferring an agent's future position. The latent intent of all agents is also jointly modeled, allowing the stochasticity in one agent's behavior to affect other agents. Our method significantly improves the state of the art on well-established pedestrian and autonomous driving datasets.

Active Tree Search in Large POMDPs Artificial Intelligence

Model-based planning and prospection are widely studied in both cognitive neuroscience and artificial intelligence (AI), but from different perspectives - and with different desiderata in mind (biological realism versus scalability) that are difficult to reconcile. Here, we introduce a novel method to plan in large POMDPs - Active Tree Search - that combines the normative character and biological realism of a leading planning theory in neuroscience (Active Inference) and the scalability of Monte-Carlo methods in AI. This unification is beneficial for both approaches. On the one hand, using Monte-Carlo planning permits scaling up the biologically grounded approach of Active Inference to large-scale problems. On the other hand, the theory of Active Inference provides a principled solution to the balance of exploration and exploitation, which is often addressed heuristically in Monte-Carlo methods. Our simulations show that Active Tree Search successfully navigates binary trees that are challenging for sampling-based methods, problems that require adaptive exploration, and the large POMDP problem Rocksample. Furthermore, we illustrate how Active Tree Search can be used to simulate neurophysiological responses (e.g., in the hippocampus and prefrontal cortex) of humans and other animals that contain large planning problems. These simulations show that Active Tree Search is a principled realisation of neuroscientific and AI theories of planning, which offers both biological realism and scalability.

A New Paradigm of Threats in Robotics Behaviors Artificial Intelligence

Robots applications in our daily life increase at an unprecedented pace. As robots will soon operate "out in the wild", we must identify the safety and security vulnerabilities they will face. Robotics researchers and manufacturers focus their attention on new, cheaper, and more reliable applications. Still, they often disregard the operability in adversarial environments where a trusted or untrusted user can jeopardize or even alter the robot's task. In this paper, we identify a new paradigm of security threats in the next generation of robots. These threats fall beyond the known hardware or network-based ones, and we must find new solutions to address them. These new threats include malicious use of the robot's privileged access, tampering with the robot sensors system, and tricking the robot's deliberation into harmful behaviors. We provide a taxonomy of attacks that exploit these vulnerabilities with realistic examples, and we outline effective countermeasures to prevent better, detect, and mitigate them.

The Inescapable Duality of Data and Knowledge Artificial Intelligence

We will discuss how over the last 30 to 50 years, systems that focused only on data have been handicapped with success focused on narrowly focused tasks, and knowledge has been critical in developing smarter, intelligent, more effective systems. We will draw a parallel with the role of knowledge and experience in human intelligence based on cognitive science. And we will end with the recent interest in neuro-symbolic or hybrid AI systems in which knowledge is the critical enabler for combining data-intensive statistical AI systems with symbolic AI systems which results in more capable AI systems that support more human-like intelligence.

Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents Artificial Intelligence

Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.