Related papers: A Self-Organized Neural Comparator

The Manual labeling of data is and will remain a costly endeavor. For this reason, semi-supervised learning remains a topic of practical importance. The recently proposed Ladder Network is one such approach that has proven to be very…

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when…

Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction…

A popular theory of perceptual processing holds that the brain learns both a generative model of the world and a paired recognition model using variational Bayesian inference. Most hypotheses of how the brain might learn these models assume…

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing…

We propose a novel biologically-plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In both, representations of objects in the same category become…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

Understanding how humans and machines learn from sparse data is central to cognitive science and machine learning. Using a species-fair design, we compare children and convolutional neural networks (CNNs) in a few-shot semi-supervised…

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a system that enables a…

Classifiers for the semi-supervised setting often combine strong supervised models with additional learning objectives to make use of unlabeled data. This results in powerful though very complex models that are hard to train and that demand…

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…

A cognitive map is an internal model which encodes the abstract relationships among entities in the world, giving humans and animals the flexibility to adapt to new situations, with a strong out-of-distribution (OOD) generalization that…

Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently citepd as strong synapse candidates due to…

Learning classifier systems are adaptive learning systems which have been widely applied in a multitude of application domains. However, there are still some generalization problems unsolved. The hurdle is that fitness and niching pressures…

Artificial neural networks which are inspired from the learning mechanism of brain have achieved great successes in many problems, especially those with deep layers. In this paper, we propose a nucleus neural network (NNN) and corresponding…

Deep graph embedding is an important approach for community discovery. Deep graph neural network with self-supervised mechanism can obtain the low-dimensional embedding vectors of nodes from unlabeled and unstructured graph data. The…

Neural networks are not learning optimal decision boundaries. We show that decision boundaries are situated in areas of low training data density. They are impacted by few training samples which can easily lead to overfitting. We provide a…

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Sensory input from multiple sources is crucial for robust and coherent human perception. Different sources contribute complementary explanatory factors. Similarly, research studies often collect multimodal imaging data, each of which can…

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a…