For decades, neuroscientists and computer scientists have pursued a shared ambition: to understand intelligence and build it. Modern artificial neural networks now rival humans in language, perception, and reasoning, yet it is still largely unknown whether these artificial systems organize information as the brain does. Existing brain-AI alignment studies have shown the striking correspondence between the two systems, but such comparisons remain bound to specific inputs and tasks, offering no common ground for comparing how AI models with different kinds of modalities-vision, language, or multimodal-are intrinsically organized. Here we introduce a groundbreaking concept of Brain-like Space: a unified geometric space in which every AI model can be precisely situated and compared by mapping its intrinsic spatial attention topological organization onto canonical human functional brain networks, regardless of input modality, task, or sensory domain. Our extensive analysis of 151 Transformer-based models spanning state-of-the-art large vision models, large language models, and large multimodal models uncovers a continuous arc-shaped geometry within this space, reflecting a gradual increase of brain-likeness; different models exhibit distinct distribution patterns within this geometry associated with different degrees of brain-likeness, shaped not merely by their modality but by whether the pretraining paradigm emphasizes global semantic abstraction and whether the positional encoding scheme facilitates deep fusion across different modalities. Moreover, the degree of brain-likeness for a model and its downstream task performance are not "identical twins". The Brain-like Space provides the first unified framework for situating, quantifying, and comparing intelligence across domains, revealing the deep organizational principles that bridge machines and the brain.

Early in development, infants learn a range of useful concepts, which can be challenging from a computational standpoint. This early learning comes together with an initial understanding of aspects of the meaning of concepts, e.g., their implications, causality, and using them to predict likely future events. All this is accomplished in many cases with little or no supervision, and from relatively few examples, compared with current network models. In learning about objects and human-object interactions, early acquired and possibly innate concepts are often used in the process of learning additional, more complex concepts. In the current work, we model how early-acquired concepts are used in the learning of subsequent concepts, and compare the results with standard deep network modeling. We focused in particular on the use of the concepts of animacy and goal attribution in learning to predict future events. We show that the use of early concepts in the learning of new concepts leads to better learning (higher accuracy) and more efficient learning (requiring less data). We further show that this integration of early and new concepts shapes the representation of the concepts acquired by the model. The results show that when the concepts were learned in a human-like manner, the emerging representation was more useful, as measured in terms of generalization to novel data and tasks. On a more general level, the results suggest that there are likely to be basic differences in the conceptual structures acquired by current network models compared to human learning.

What is AI bias and how can it affect human rights? In this blog post, we explore AI bias examples, challenges, and why the answer lies in ethical AI.

This paper briefly analyzes the advantages and problems of AI mainstream technology and puts forward: To achieve stronger Artificial Intelligence, the end-to-end function calculation must be changed and adopt the technology system centered on scene fitting. It also discusses the concrete scheme named Dynamic Cognitive Network model (DC Net). Discussions : The knowledge and data in the comprehensive domain are uniformly represented by using the rich connection heterogeneous Dynamic Cognitive Network constructed by conceptualized elements; A network structure of two dimensions and multi layers is designed to achieve unified implementation of AI core processing such as combination and generalization; This paper analyzes the implementation differences of computer systems in different scenes, such as open domain, closed domain, significant probability and non-significant probability, and points out that the implementation in open domain and significant probability scene is the key of AI, and a cognitive probability model combining bidirectional conditional probability, probability passing and superposition, probability col-lapse is designed; An omnidirectional network matching-growth algorithm system driven by target and probability is designed to realize the integration of parsing, generating, reasoning, querying, learning and so on; The principle of cognitive network optimization is proposed, and the basic framework of Cognitive Network Learning algorithm (CNL) is designed that structure learning is the primary method and parameter learning is the auxiliary. The logical similarity of implementation between DC Net model and human intelligence is analyzed in this paper.

We managed to use machine learning to develop face recognition, games intelligence, self driving vehicles or language translation. With mathematically generated patterns similar to the brain neurons, these systems can learn and perform actions similar to humans or even better. It's a huge evidence that this approach is working and the model we have copied from the brain is valid. We knew that one day, we will reach for the moon when we created the first plane or the first rocket. Today, we know that one day, we will build intelligent machines - we just don't know how long it's going to take. We are somehow designed to create intelligent beings. All discoveries today seem to head us there and we cannot stop this progress.

Cognition is the process of knowing. As carried out by a dynamical system, it is the process by which the system absorbs information into its state. A complex network of agents cognizes knowledge about its environment, internal dynamics and initial state by forming emergent, macro-level patterns. Such patterns require each agent to find its place while partially aware of the whole pattern. Such partial awareness can be achieved by separating the system dynamics into two parts by timescale: the propagation dynamics and the pattern dynamics. The fast propagation dynamics describe the spread of signals across the network. If they converge to a fixed point for any quasi-static state of the slow pattern dynamics, that fixed point represents an aggregate of macro-level information. On longer timescales, agents coordinate via positive feedback to form patterns, which are defined using closed walks in the graph of agents. Patterns can be coherent, in that every part of the pattern depends on every other part for context. Coherent patterns are acausal, in that (a) they cannot be predicted and (b) no part of the stored knowledge can be mapped to any part of the pattern, or vice versa. A cognitive network's knowledge is encoded or embodied by the selection of patterns which emerge. The theory of cognition summarized here can model autocatalytic reaction-diffusion systems, artificial neural networks, market economies and ant colony optimization, among many other real and virtual systems. This theory suggests a new understanding of complexity as a lattice of contexts rather than a single measure.

Human parsing is an important task for human-centric understanding. Generally, two mainstreams are used to deal with this challenging and fundamental problem. The first one is employing extra human pose information to generate hierarchical parse graph to deal with human parsing task. Another one is training an end-to-end network with the semantic information in image level. In this paper, we develop an end-to-end progressive cognitive network to segment human parts. In order to establish a hierarchical relationship, a novel component-aware region convolution structure is proposed. With this structure, latter layers inherit prior component information from former layers and pay its attention to a finer component. In this way, we deal with human parsing as a progressive recognition task, that is, we first locate the whole human and then segment the hierarchical components gradually. The experiments indicate that our method has a better location capacity for the small objects and a better classification capacity for the large objects. Moreover, our framework can be embedded into any fully convolutional network to enhance the performance significantly.

Attitudes play a significant role in determining how individuals process information and behave. In this paper we have developed a new computational model of population wide attitude change that captures the social level: how individuals interact and communicate information, and the cognitive level: how attitudes and concept interact with each other. The model captures the cognitive aspect by representing each individuals as a parallel constraint satisfaction network. The dynamics of this model are explored through a simple attitude change experiment where we vary the social network and distribution of attitudes in a population.

In this work an AI/ICT Platform is presented, to develop cognitive networks to cope with a management of a great availability of data and a necessity to dispose of prompt right information, extracted by data. In fact, the better strategic decision arise by a prompt availability of target and effective information. A cognitive network, and in particular an intelligent grid, helps to reach this goal. This intelligent grid allows to integrate many data source to drive analytics which transform data into useful information to support advanced operational control and strategic decision making. To realize an intelligent grid, it is necessary, firstly, capturing Knowledge, transforming data in information and introducing the knowledge in ICT framework and in Real-Time Systems. This is the right way to have a set of target and suitable information by using to take a correct decision, especially in real-time problem. So, in this work XBASE Cognitive Mapping Tool is presented. This tool allows to develop an intelligent grid, to support and “automate” strategic decision and so, to solve, also in real-time, every kind of problems. In particular, an application of this tool is presented, in monitoring of wastewater, the “BATTLE” Project.