Computation in recurrent networks of neurons has been hypothesized to occur at the level of low-dimensional latent dynamics, both in artificial systems and in the brain. This hypothesis seems at odds with evidence from large-scale neuronal recordings in mice showing that neuronal population activity is high-dimensional. To demonstrate that low-dimensional latent dynamics and high-dimensional activity can be two sides of the same coin, we present an analytically solvable recurrent neural network (RNN) model whose dynamics can be exactly reduced to a lowdimensional dynamical system, but generates an activity manifold that has a high linear embedding dimension. This raises the question: Do low-dimensional latents explain the high-dimensional activity observed in mouse visual cortex? Spectral theory tells us that the covariance eigenspectrum alone does not allow us to recover the dimensionality of the latents, which can be low or high, when neurons are nonlinear. To address this indeterminacy, we develop Neural Cross-Encoder (NCE), an interpretable, nonlinear latent variable modeling method for neuronal recordings, and find that high-dimensional neuronal responses to drifting gratings and spontaneous activity in visual cortex can be reduced to low-dimensional latents, while the responses to natural images cannot. We conclude that the high-dimensional activity measured in certain conditions, such as in the absence of a stimulus, is explained by low-dimensional latents that are nonlinearly processed by individual neurons.

Neurons encode information in a binary manner and process complex signals. However, predicting or generating diverse neural activity patterns remains challenging. In vitro and in vivo studies provide distinct advantages, yet no robust computational framework seamlessly integrates both da ta types. We address this by applying the Transformer model, widely used in large - scale language models, to neural data. To handle binary data, we introduced Dice loss, enabling accurate cross - domain neural activity generation. Structural analysis revealed how Dice loss enhances learning and identified key brain regions facilitating high - precision data generation. Our findings support the 3Rs principle in animal research, particularly Replacement, and establish a mathematical framework bridging animal experiments and human clinical studies. This work advances data - driven neuroscience and neural activity modeling, pa ving the way for more ethical and effective experimental methodologies. 2

Biological neural networks are characterized by their high degree of plasticity, a core property that enables the remarkable adaptability of natural organisms. Importantly, this ability affects both the synaptic strength and the topology of the nervous systems. Artificial neural networks, on the other hand, have been mainly designed as static, fully connected structures that can be notoriously brittle in the face of changing environments and novel inputs. Building on previous works on Neural Developmental Programs (NDPs), we propose a class of self-organizing neural networks capable of synaptic and structural plasticity in an activity and reward-dependent manner which we call Lifelong Neural Developmental Program (LNDP). We present an instance of such a network built on the graph transformer architecture and propose a mechanism for pre-experience plasticity based on the spontaneous activity of sensory neurons. Our results demonstrate the ability of the model to learn from experiences in different control tasks starting from randomly connected or empty networks. We further show that structural plasticity is advantageous in environments necessitating fast adaptation or with non-stationary rewards.

We here analyse the question of developing artificial consciousness from an evolutionary perspective, taking the evolution of the human brain and its relation with consciousness as a reference model. This kind of analysis reveals several structural and functional features of the human brain that appear to be key for reaching human-like complex conscious experience and that current research on Artificial Intelligence (AI) should take into account in its attempt to develop systems capable of conscious processing. We argue that, even if AI is limited in its ability to emulate human consciousness for both intrinsic (structural and architectural) and extrinsic (related to the current stage of scientific and technological knowledge) reasons, taking inspiration from those characteristics of the brain that make conscious processing possible and/or modulate it, is a potentially promising strategy towards developing conscious AI. Also, it is theoretically possible that AI research can develop partial or potentially alternative forms of consciousness that is qualitatively different from the human, and that may be either more or less sophisticated depending on the perspectives. Therefore, we recommend neuroscience-inspired caution in talking about artificial consciousness: since the use of the same word consciousness for humans and AI becomes ambiguous and potentially misleading, we propose to clearly specify what is common and what differs in AI conscious processing from full human conscious experience.

A powerful symbiotic relationship has blossomed between neuroscience and computer science as of late, with brain systems providing inspiration for prevalent computer algorithms like neural networks and computer-based mathematical models driving important research into the brain's computational methods. Daniel Kahneman's Thinking, Fast and Slow, has popularized the notion that human cognition is divided into distinct hierarchical systems, which Kahneman deems "system 1" and "system 2." Artificial intelligence can handle system 1 tasks, pertaining to fast, nonconscious operations, just as efficiently as humans can. However, it still lags behind when it comes to system 2 tasks, which engage different cognitive pathways that are slower and enlist conscious deliberation. The fact that computers can't compete with humans at deliberate tasks means that computer scientists still have a lot to learn from the brain, which inspired researchers out of the Sorbonne to develop a computational model based on the most recent theories in human learning and cognitive development. They found that processes like synaptic pruning (the elimination of underused synapses), neurogenesis, and energy regulation, and accurate dopamine reinforcement were underrepresented in computational learning models.

Our current era is now in the so-called third artificial intelligence (AI) boom. Professor Hirokazu Takahashi has been engaged in brain research using the techniques of reverse engineering, an approach that strives to shed light on the underlying structure of products by taking them apart. According to Takahashi, there are two types of intellectual cleverness, and fundamental differences distinguish our brains from artificial intelligence. In rat experiments, "futility" or "uselessness" is a key word that frequently comes into perspective. If we understand the features of the brain, is it not "futile" to be "uselessly" fearful of AI?

This article reviews how organisms learn and recognize the world through the dynamics of neural networks from the perspective of Bayesian inference, and introduces a view on how such dynamics is described by the laws for the entropy of neural activity, a paradigm that we call thermodynamics of the Bayesian brain. The Bayesian brain hypothesis sees the stimulus-evoked activity of neurons as an act of constructing the Bayesian posterior distribution based on the generative model of the external world that an organism possesses. A closer look at the stimulus-evoked activity at early sensory cortices reveals that feedforward connections initially mediate the stimulus-response, which is later modulated by input from recurrent connections. Importantly, not the initial response, but the delayed modulation expresses animals' cognitive states such as awareness and attention regarding the stimulus. Using a simple generative model made of a spiking neural population, we reproduce the stimulus-evoked dynamics with the delayed feedback modulation as the process of the Bayesian inference that integrates the stimulus evidence and a prior knowledge with time-delay. We then introduce a thermodynamic view on this process based on the laws for the entropy of neural activity. This view elucidates that the process of the Bayesian inference works as the recently-proposed information-theoretic engine (neural engine, an analogue of a heat engine in thermodynamics), which allows us to quantify the perceptual capacity expressed in the delayed modulation in terms of entropy.

One of the core challenges of modern AI can be demonstrated with a rotating yellow school bus. When viewed head-on on a country road, a deep-learning neural network confidently and correctly identifies the bus. When it is laid on its side across the road, though, the algorithm believes--again, with high confidence--that it's a snowplow. Seen from underneath and at an angle, it is definitely a garbage truck. The problem is one of context. When a new image is sufficiently different from the set of training images, deep learning visual recognition stumbles, even if the difference comes down to a simple rotation or obstruction.

How are the spatial patterns of spontaneous and evoked population responses related? We study the impact of connectivity on the spatial pattern of fluctuations in the input-generated response of a neural network, by comparing the distribution of evoked and intrinsically generated activity across the different units. We develop a complementary approach to principal component analysis in which separate high-variance directions are typically derived for each input condition. We analyze subspace angles to compute the difference between the shapes of trajectories corresponding to different network states, and the orientation of the low-dimensional subspaces that driven trajectories occupy within the full space of neuronal activity. In addition to revealing how the spatiotemporal structure of spontaneous activity affects input-evoked responses, these methods can be used to infer input selectivity induced by network dynamics from experimentally accessible measures of spontaneous activity (e.g. from voltage- or calcium-sensitive optical imaging experiments). We conclude that the absence of a detailed spatial map of afferent inputs and cortical connectivity does not limit our ability to design spatially extended stimuli that evoke strong responses.

A neurotrophic model for the co-development of topography and ocular dominance columns in the primary visual cortex has recently been proposed. In the present work, we test this model by driving it with the output of a pair of neuronal vision sensors stimulated by disparate moving patterns. We show that the temporal correlations in the spike trains generated by the two sensors elicit the development of refined topography and ocular dominance columns, even in the presence of significant amounts of spontaneous activity and fixed-pattern noise in the sensors.