We present an unsupervised deep learning model for 3D object classification. Conventional Hebbian learning, a well-known unsupervised model, suffers from loss of local features leading to reduced performance for tasks with complex geometric objects. We present a deep network with a novel Neuron Activity Aware (NeAW) Hebbian learning rule that dynamically switches the neurons to be governed by Hebbian learning or anti-Hebbian learning, depending on its activity. We analytically show that NeAW Hebbian learning relieves the bias in neuron activity, allowing more neurons to attend to the representation of the 3D objects. Empirical results show that the NeAW Hebbian learning outperforms other variants of Hebbian learning and shows higher accuracy over fully supervised models when training data is limited. Supervised deep networks for recognizing objects from 3D point clouds have demonstrated high accuracy but generally suffer from poor performance when labeled training data is limited (Wu et al., 2015; Qi et al., 2017a;b; Wang et al., 2019; Maturana & Scherer, 2015). On the other hand, self-supervised or unsupervised models can be trained without labeled data hence improving the performance in data efficient scenarios. Self-supervised learning methods have been studied for 3D object recognition mostly in an autoencoder setting, which necessarily reconstructs input to learn the representation (Achlioptas et al., 2018; Girdhar et al., 2016). Unsupervised learning has also been applied to pre-process the input for an encoder but still largely relying on supervised learning (Li et al., 2018). Conventionally, self-organizing maps and growing neural gas have been used as fully unsupervised learning for 3D objects while they aim to reconstruct the surface of the objects (do Rêgo et al., 2007; Mole & Araújo, 2010). A fully unsupervised deep network for 3D object classification has rarely been studied. Unsupervised Hebbian learning is known to offer attractive advantages such as data efficiency, noise robustness, and adaptability for various applications (Najarro & Risi, 2020; Kang et al., 2022; Miconi et al., 2018; Zhou et al., 2022). The basic Hebbian and anti-Hebbian learning refer to that synaptic weight is strengthened and weakened, respectively, when pre-and post-synaptic neurons are simultaneously activated (Hebb, 2005). Many past efforts have developed variants of Hebb's rule.

Here we aimed to use biologically relevant neuron models connected in a brain-like network structure to study its potential to achieve input separation in a robotic system interacting with real-world objects. The model network was inspired by local cortical networks in its recursive structure in principle, though with much fewer neurons and without the ambition to precisely mimick any assumed specific network structure. The aim was to explore if the inherent dynamic properties in such networks in themselves were enough to achieve efficient object classification. Our model system is reminiscent of Reservoir Computing networks (i.e. Gauthier et al 2020 Nature Communications), but our neurons have state memory, i.e. dynamics, which are biologically relevant. Moreover, the population of neurons are split into excitatory and inhibitory neurons. Combined with the neuronal output thresholding, i.e. imparting nonlinearity to the networks when inhibition drives the neurons below their thresholds, and combined with biologically relevant conduction delays, this setting creates extraordinarily rich network dynamics. Motivation for: what would be required in the robotics design to explore the questions we set out to explore? How well could we live up to those requirements with the robotics system used?

Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system. In this paper, we present a novel Hebbian learning method to extract the global feature of point sets in StarCraft II game units, and its application to predict the movement of the points. Our model includes encoder, LSTM, and decoder, and we train the encoder with the unsupervised learning method. We introduce the concept of neuron activity aware learning combined with k-Winner-Takes-All. The optimal value of neuron activity is mathematically derived, and experiments support the effectiveness of the concept over the downstream task. Our Hebbian learning rule benefits the prediction with lower loss compared to self-supervised learning. Also, our model significantly saves the computational cost such as activations and FLOPs compared to a frame-based approach.

A lab, whose work is concentrated on neuromorphic computing or brain-inspired computing, has new research that introduces hardware improvements by harnessing a quality known as 'randomness' or 'stochasticity'. Their research contradicts the perception of randomness as a quality that will negatively impact computation results and demonstrates the utilization of finely controlled stochastic features in semiconductor devices to improve performing optimization. This has potential to create a more sophisticated building block for creating computers that can tackle sophisticated optimization problems, which can potentially be more efficient. What's more they can consume less power.

The mammalian brain could contain dense and sparse network connectivity structures, including both excitatory and inhibitory neurons, but is without any clearly defined output layer. The neurons have time constants, which mean that the integrated network structure has state memory. The network structure contains complex mutual interactions between the neurons under different conditions, which depend on the internal state of the network. The internal state can be defined as the distribution of activity across all individual neurons across the network. Therefore, the state of a neuron/network becomes a defining factor for how information is represented within the network. Towards this study, we constructed a fully connected (with dense/sparse coding strategies) recurrent network comprising of both excitatory and inhibitory neurons, driven by pseudo-random inputs of varying frequencies. In this study we assessed the impact of varying specific intrinsic parameters of the neurons that enriched network state dynamics, such as initial neuron activity, amount of inhibition in combination with thresholded neurons and conduction delays. The impact was assessed by quantifying the changes in mutual interactions between the neurons within the network for each given input. We found such effects were more profound in sparsely connected networks than in densely connected networks. However, also densely connected networks could make use of such dynamic changes in the mutual interactions between neurons, as a given input could induce multiple different network states.

Identification of patterns from discrete data time-series for statistical inference, threat detection, social opinion dynamics, brain activity prediction has received recent momentum. In addition to the huge data size, the associated challenges are, for example, (i) missing data to construct a closed time-varying complex network, and (ii) contribution of unknown sources which are not probed. Towards this end, the current work focuses on statistical neuron system model with multi-covariates and unknown inputs. Previous research of neuron activity analysis is mainly limited with effects from the spiking history of target neuron and the interaction with other neurons in the system while ignoring the influence of unknown stimuli. We propose to use unknown unknowns, which describes the effect of unknown stimuli, undetected neuron activities and all other hidden sources of error. The maximum likelihood estimation with the fixed-point iteration method is implemented. The fixed-point iterations converge fast, and the proposed methods can be efficiently parallelized and offer computational advantage especially when the input spiking trains are over long time-horizon. The developed framework provides an intuition into the meaning of having extra degrees-of-freedom in the data to support the need for unknowns. The proposed algorithm is applied to simulated spike trains and on real-world experimental data of mouse somatosensory, mouse retina and cat retina. The model shows a successful increasing of system likelihood with respect to the conditional intensity function, and it also reveals the convergence with iterations. Results suggest that the neural connection model with unknown unknowns can efficiently estimate the statistical properties of the process by increasing the network likelihood.