arXiv research

Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces…

In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM). In the multi-clustering integration module, we apply three unsupervised K-means, affinity propagation and spectral c…

LIFE framework improves model accuracy and interpretability.

To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer. The GBN's hidd…

We study how finite Bayesian neural networks adapt their hidden representations.

New method discovers concepts in hidden feature layers using sparse subspace clustering.

Recent results in nonparametric regression show that deep learning, i.e., neural network estimates with many hidden layers, are able to circumvent the so-called curse of dimensionality in case that suitable restrictions on the structure of the regression function hold. One key feature of the neural networks used in the…

It is widely believed that the backpropagation algorithm is essential for learning good feature detectors in early layers of artificial neural networks, so that these detectors are useful for the task performed by the higher layers of that neural network. At the same time, the traditional form of backpropagation is bio…

New CFNN architecture approximates functions with machine accuracy.

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on th…

Algorithm predicts performance of learning in multi-layer networks with matrix-valued hidden variables.

Neural networks favor simple features over complex ones, even when complex features are available.

CoulGAT interprets GAT models by analyzing node interactions.

New framework identifies hidden risks and optionality in American options.

Generative model initializes 2-layer network weights for small datasets.

Learning and inferring features that generate sensory input is a task continuously performed by cortex. In recent years, novel algorithms and learning rules have been proposed that allow neural network models to learn such features from natural images, written text, audio signals, etc. These networks usually involve de…

A new tensor-based layer reduces neural network dimensions without losing important features.

We show that a collection of Gaussian mixture models (GMMs) in $R^{n}$ can be optimally classified using $O(n)$ neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least $O(\exp(n))$ neurons …

DNNs with $L_{2}$ regularization reveal feature learning dynamics and sparsity.

Deep neural networks show some layers better align with data than others.

Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. We make an attempt to boost the classification performance by studying a new formulation in deep networks. Three aspects in convolutional neural netwo…

Hierarchical probabilistic models are able to use a large number of parameters to create a model with a high representation power. However, it is well known that increasing the number of parameters also increases the complexity of the model which leads to a bias-variance trade-off. Although it is a classical problem, t…

To infer a multilayer representation of high-dimensional count vectors, we propose the Poisson gamma belief network (PGBN) that factorizes each of its layers into the product of a connection weight matrix and the nonnegative real hidden units of the next layer. The PGBN's hidden layers are jointly trained with an upwar…

3-layer NTK models generalize better than 2-layer models, especially with large input dimensions.

Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…

Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. Bu…

New framework analyzes deep neural networks using feature probabilities.

Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by feeding patches of the data into a recurrent neural network and using the outputs or…

Self-regularizing RBMs learn optimal hidden units efficiently.

Consider a feedforward neural network $ψ: \mathbb{R}^d\rightarrow \mathbb{R}^d$ such that $ψ\approx \nabla f$, where $f:\mathbb{R}^d \rightarrow \mathbb{R}$ is a smooth function, therefore $ψ$ must satisfy $\partial_j ψ_i = \partial_i ψ_j$ pointwise. We prove a theorem that a $ψ$ network with more than one hidden layer…

Formula found for neural network error with fixed weights.

Universal MLPs with a single hidden layer can learn any function.

Characterizes test error in learning with deep, structured feature maps.

Transferability of learned features between tasks can massively reduce the cost of training a neural network on a novel task. We investigate the effect of network width on learned features using activation atlases --- a visualization technique that captures features the entire hidden state responds to, as opposed to in…

Enhanced feature learning using neural networks and kernel methods with improved robustness.

Two-layer networks favor simple features, especially in complex datasets.

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…

A neural network with a single hidden layer can't represent certain multivariable functions.

Recent results on optimization and generalization properties of neural networks showed that in a simple two-layer network, the alignment of the labels to the eigenvectors of the corresponding Gram matrix determines the convergence of the optimization during training. Such analyses also provide upper bounds on the gener…

Improved DNN calibration without sacrificing accuracy.

Graph cross network improves graph classification accuracy.

Study explores how neural networks and Transformers learn modular arithmetic with multiple inputs.

In this paper we propose a function space approach to Representation Learning and the analysis of the representation layers in deep learning architectures. We show how to compute a weak-type Besov smoothness index that quantifies the geometry of the clustering in the feature space. This approach was already applied suc…

Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings. General Linear Models (GLMs) are self-explaining because the model weights directly show how each feature contributes to the output value. H…

Chemical networks outperform spiking neural networks in classification tasks.

FedMA improves federated learning for neural nets, matching and averaging model elements.

Binary autoencoder with sparse hidden layer preserves information and zero reconstruction error.

A new algorithm learns from raw feature vectors using deep neural networks and UCB for exploration.