Goto

Collaborating Authors

Cognitive Architectures


Whole brain Probabilistic Generative Model toward Realizing Cognitive Architecture for Developmental Robots

arXiv.org Artificial Intelligence

Through the developmental process, they acquire basic physical skills (such as reaching and grasping), perceptional skills (such as object recognition and phoneme recognition), and social skills (such as linguistic communication and intention estimation) (Taniguchi et al., 2018). This open-ended online learning process involving many types of modalities, tasks, and interactions is often referred to as lifelong learning (Oudeyer et al., 2007; Parisi et al., 2019). The central question in next-generation artificial intelligence (AI) and developmental robotics is how to build an integrative cognitive system that is capable of lifelong learning and humanlike behavior in environments such as homes, offices, and outdoor. In this paper, inspired by the human whole brain architecture (WBA) approach, we introduce the idea of building an integrative cognitive system using a whole brain probabilistic generative model (WB-PGM) (see 2.1). The integrative cognitive system can alternatively be referred to as artificial general intelligence (AGI) (Yamakawa, 2021). Against this backdrop, we explore the process of establishing a cognitive architecture for developmental robots. Cognitive architecture is a hypothesis about the mechanisms of human intelligence underlying our behaviors (Rosenbloom, 2011). The study of cognitive architecture involves developing a presumably standard model of the humanlike mind (Laird et al., 2017).


Towards Human-Like Automated Test Generation: Perspectives from Cognition and Problem Solving

arXiv.org Artificial Intelligence

Automated testing tools typically create test cases that are different from what human testers create. This often makes the tools less effective, the created tests harder to understand, and thus results in tools providing less support to human testers. Here, we propose a framework based on cognitive science and, in particular, an analysis of approaches to problem-solving, for identifying cognitive processes of testers. The framework helps map test design steps and criteria used in human test activities and thus to better understand how effective human testers perform their tasks. Ultimately, our goal is to be able to mimic how humans create test cases and thus to design more human-like automated test generation systems. We posit that such systems can better augment and support testers in a way that is meaningful to them.


Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma

arXiv.org Artificial Intelligence

Simulations, along with other similar applications like virtual worlds and video games, require computational models of intelligence that generate realistic and credible behavior for the participating synthetic characters. Cognitive architectures, which are models of the fixed structure underlying intelligent behavior in both natural and artificial systems, provide a conceptually valid common basis, as evidenced by the current efforts towards a standard model of the mind, to generate human-like intelligent behavior for these synthetic characters. Sigma is a cognitive architecture and system that strives to combine what has been learned from four decades of independent work on symbolic cognitive architectures, probabilistic graphical models, and more recently neural models, under its graphical architecture hypothesis. Sigma leverages an extended form of factor graphs towards a uniform grand unification of not only traditional cognitive capabilities but also key non-cognitive aspects, creating unique opportunities for the construction of new kinds of cognitive models that possess a Theory-of-Mind and that are perceptual, autonomous, interactive, affective, and adaptive. In this paper, we will introduce Sigma along with its diverse capabilities and then use three distinct proof-of-concept Sigma models to highlight combinations of these capabilities: (1) Distributional reinforcement learning models in; (2) A pair of adaptive and interactive agent models that demonstrate rule-based, probabilistic, and social reasoning; and (3) A knowledge-free exploration model in which an agent leverages only architectural appraisal variables, namely attention and curiosity, to locate an item while building up a map in a Unity environment.


Linguistic calibration through metacognition: aligning dialogue agent responses with expected correctness

arXiv.org Artificial Intelligence

Open-domain dialogue agents have vastly improved, but still confidently hallucinate knowledge or express doubt when asked straightforward questions. In this work, we analyze whether state-of-the-art chit-chat models can express metacognition capabilities through their responses: does a verbalized expression of doubt (or confidence) match the likelihood that the model's answer is incorrect (or correct)? We find that these models are poorly calibrated in this sense, yet we show that the representations within the models can be used to accurately predict likelihood of correctness. By incorporating these correctness predictions into the training of a controllable generation model, we obtain a dialogue agent with greatly improved linguistic calibration.


Distributed Adaptive Control: An ideal Cognitive Architecture candidate for managing a robotic recycling plant

arXiv.org Artificial Intelligence

In the past decade, society has experienced notable growth in a variety of technological areas. However, the Fourth Industrial Revolution has not been embraced yet. Industry 4.0 imposes several challenges which include the necessity of new architectural models to tackle the uncertainty that open environments represent to cyber-physical systems (CPS). Waste Electrical and Electronic Equipment (WEEE) recycling plants stand for one of such open environments. Here, CPSs must work harmoniously in a changing environment, interacting with similar and not so similar CPSs, and adaptively collaborating with human workers. In this paper, we support the Distributed Adaptive Control (DAC) theory as a suitable Cognitive Architecture for managing a recycling plant. Specifically, a recursive implementation of DAC (between both singleagent and large-scale levels) is proposed to meet the expected demands of the European Project HR-Recycler. Additionally, with the aim of having a realistic benchmark for future implementations of the recursive DAC, a micro-recycling plant prototype is presented. Keywords: Cognitive Architecture, Distributed Adaptive Control, Recycling Plant, Navigation, Motor Control, Human-Robot Interaction.


Learning a metacognition for object perception

arXiv.org Artificial Intelligence

Beyond representing the external world, humans also represent their own cognitive processes. In the context of perception, this metacognition helps us identify unreliable percepts, such as when we recognize that we are seeing an illusion. Here we propose MetaGen, a model for the unsupervised learning of metacognition. In MetaGen, metacognition is expressed as a generative model of how a perceptual system produces noisy percepts. Using basic principles of how the world works (such as object permanence, part of infants' core knowledge), MetaGen jointly infers the objects in the world causing the percepts and a representation of its own perceptual system. MetaGen can then use this metacognition to infer which objects are actually present in the world. On simulated data, we find that MetaGen quickly learns a metacognition and improves overall accuracy, outperforming models that lack a metacognition.


A Neural Dynamic Model based on Activation Diffusion and a Micro-Explanation for Cognitive Operations

arXiv.org Artificial Intelligence

The neural mechanism of memory has a very close relation with the problem of representation in artificial intelligence. In this paper a computational model was proposed to simulate the network of neurons in brain and how they process information. The model refers to morphological and electrophysiological characteristics of neural information processing, and is based on the assumption that neurons encode their firing sequence. The network structure, functions for neural encoding at different stages, the representation of stimuli in memory, and an algorithm to form a memory were presented. It also analyzed the stability and recall rate for learning and the capacity of memory. Because neural dynamic processes, one succeeding another, achieve a neuron-level and coherent form by which information is represented and processed, it may facilitate examination of various branches of Artificial Intelligence, such as inference, problem solving, pattern recognition, natural language processing and learning. The processes of cognitive manipulation occurring in intelligent behavior have a consistent representation while all being modeled from the perspective of computational neuroscience. Thus, the dynamics of neurons make it possible to explain the inner mechanisms of different intelligent behaviors by a unified model of cognitive architecture at a micro-level.


Red Box Delivers Cloud Configurable Voice Recording to Fuel AI on Microsoft Azure

#artificialintelligence

Red Box, a leading platform for voice, announces an extension of its relationship with Microsoft aligned to the launch of Conversa, Red Box's enterprise voice platform. Red Box is already a Preferred Telephony Partner for conversation intelligence, part of Microsoft Dynamics 365 Sales and Customer Service. This latest development in the relationship delivers a unique capture layer for enterprise voice. It combines the power of Conversa audio processing in Microsoft Azure and Microsoft AI, with seamless support of both cloud and premise-based telephony aligned with frictionless zero touch implementations. The on-premise self-install capability provided by Conversa, and powered by Azure Cloud, will simplify the delivery of'AI-Ready', real-time voice capture for those organizations that struggle to gain access to audio data.


6 Major Branches of Artificial Intelligence (AI)

#artificialintelligence

"Artificial Intelligence (AI) is the part of computer science concerned with designing intelligent computer systems, that is, systems that exhibit characteristics we associate with intelligence in human behavior – understanding language, learning, reasoning, solving problems, and so on." Artificial intelligence is the practice of computer recognition, reasoning, and action. It is all about bestowing machines the power of simulating human behavior, notably cognitive capacity. However, Artificial intelligence, Machine learning, and Data Science are all related to each other. In the commencement of this blog, we will gain expertise in Artificial Intelligence and its major six branches.


Broadvoice Strengthens Channel Team

#artificialintelligence

Broadvoice, an award-winning provider of hosted voice, unified communications (UC), and SIP trunking services for businesses, is reinforcing its commitment to its indirect sales partners with the addition of two new regional sales professionals to its channel management team. Robert Sanchez joins Broadvoice as Regional Channel Manager – Mountain West and Joseph Galluzzi is now Regional Channel Manager – Northeast. Broadvoice also has regional channel managers in California, Southwest, Midwest, and Southeast. "As a channel-first organization, Broadvoice continues to expand its partner community, so we're adding resources and expertise to stay ahead of growing demand," said Kim McLachlan, Senior Vice President of Sales and Marketing. "We're pleased to welcome two veteran telecom sales professionals to the Broadvoice team to provide in-region sales support."