Related papers: Brain-Like Object Recognition with High-Performing…

Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the…

As our understanding of the mechanisms of brain function is enhanced, the value of insights gained from neuroscience to the development of AI algorithms deserves further consideration. Here, we draw parallels with an existing tree-based ANN…

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal…

Humans are able to categorize images very efficiently, in particular to detect the presence of an animal very quickly. Recently, deep learning algorithms based on convolutional neural networks (CNNs) have achieved higher than human accuracy…

Computational models are an essential tool for understanding the origin and functions of the topographic organisation of the primate visual system. Yet, vision is most commonly modelled by convolutional neural networks that ignore…

Recent research has suggested that the brain is more shallow than previously thought, challenging the traditionally assumed hierarchical structure of the ventral visual pathway. Here, we demonstrate that optimizing convolutional network…

Spiking neural networks (SNNs) have shown advantages in computation and energy efficiency over traditional artificial neural networks (ANNs) thanks to their event-driven representations. SNNs also replace weight multiplications in ANNs with…

Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continual learning, is also critical for deep neural networks (DNNs)…

Biological neurons communicate with a sparing exchange of pulses - spikes. It is an open question how real spiking neurons produce the kind of powerful neural computation that is possible with deep artificial neural networks, using only so…

Optical transmission spectroscopy is one method to understand brain tissue structural properties from brain tissue biopsy samples, yet manual interpretation is resource intensive and prone to inter observer variability. Deep convolutional…

Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from researchers and industry. The most efficient way to train deep SNNs is through ANN-SNN conversion. However, the…

In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon…

In contrast to human vision, artificial neural networks (ANNs) remain relatively susceptible to adversarial attacks. To address this vulnerability, efforts have been made to transfer inductive bias from human brains to ANNs, often by…

Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimization in convolutional neural networks (CNN) and identify the…

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural…

Spiking Neural Networks (SNNs) are considered as a potential candidate for the next generation of artificial intelligence with appealing characteristics such as sparse computation and inherent temporal dynamics. By adopting architectures of…

Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances. Artificial pattern recognizers also strive to achieve this, e.g., through translational invariance in…

Deep convolutional neural networks (DCNNs) and the ventral visual pathway share vast architectural and functional similarities in visual challenges such as object recognition. Recent insights have demonstrated that both hierarchical…

As deep learning models scale, they become increasingly competitive from domains spanning from computer vision to natural language processing; however, this happens at the expense of efficiency since they require increasingly more memory…

While Artificial Neural Networks (ANNs) have yielded impressive results in the realm of simulated intelligent behavior, it is important to remember that they are but sparse approximations of Biological Neural Networks (BNNs). We go beyond…