A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper interprets ResNets via gate-network controls and deep-layer classifications.
Study on functions computed by deep-layered machines finds same distribution in neural networks and Boolean circuits.
RevDEQs improve performance on tasks with exact gradients and fewer function evaluations.
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this…
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain shift between the training and the test data distribution. In this regard, unsup…
Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server c…
Layer-wise networks have a closed-form solution and a stopping criterion.
Layer-wise networks have a closed-form solution and a stopping criterion.
In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and pro…
This study investigates how much knowledge from natural images can be transferred to pathology images.
In this paper we develop a statistical theory and an implementation of deep learning models. We show that an elegant variable splitting scheme for the alternating direction method of multipliers optimises a deep learning objective. We allow for non-smooth non-convex regularisation penalties to induce sparsity in parame…
The paper demonstrates the use of the fully convolutional neural network for glioma segmentation on the BraTS 2019 dataset. Three-layers deep encoder-decoder architecture is used along with dense connection at encoder part to propagate the information from coarse layer to deep layers. This architecture is used to train…
Localization of chest pathologies in chest X-ray images is a challenging task because of their varying sizes and appearances. We propose a novel weakly supervised method to localize chest pathologies using class aware deep multiscale feature learning. Our method leverages intermediate feature maps from CNN layers at di…
Theory explains how deep nets learn features from data.
This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity. Pretrained networks, namely, AudioSet Net, VoxCeleb Net and Deep Speech Net trained extensively for different speech…
Deep learning depends on tuning layers near critical points.
We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix. We measure this non-linearity by applying non-negative factorization to the activation matrix. Considering…
Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, …
LogDet estimator improves entropy estimation in neural networks.
We present trellis networks, a new architecture for sequence modeling. On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent network…
ReduNet optimizes data compression by maximizing rate reduction in deep networks.
DeeperGCN tackles deep GCNs by overcoming vanishing gradient and over-smoothing issues.
A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal, fixed feature extractors that, used as the first stage of any deep network, work w…
Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing - data processing domains in which humans have long held clear advantages…
A new method generates natural-looking adversarial examples by bounding internal activation values.
New approach to abstract neural network representations using renormalization group.
Graph transformers outperform graph convolutions by preserving community information.
The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing fo…
CAggNet improves medical image segmentation by fusing coarse and fine features.
The paper tackles decision making problems with funnel structure in email marketing campaigns.
SINF models transform arbitrary PDFs to target PDFs using 1D slices.
Statistical neurodynamics studies macroscopic behaviors of randomly connected neural networks. We consider a deep layered feedforward network where input signals are processed layer by layer. The manifold of input signals is embedded in a higher dimensional manifold of the next layer as a curved submanifold, provided t…
EigenGAN discovers interpretable dimensions in GAN layers for semantic control.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
A study on the depth of graph neural networks on sparse graphs, revealing a dichotomy based on the Kesten-Stigum ratio.
The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss while significantly reducing the memory footprint and compute intensity of the DN…
Feedback alignment methods need to be evaluated for accuracy and gradient cosine similarity.
In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying t…
Dual-stage sEMG classification improves gesture recognition accuracy.
A novel method for classification with rejection using ensemble of cost-sensitive classifiers.
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Sequence classification is an important data mining task in many real world applications. Over the past few decades, many sequence classification methods have been proposed from different aspects. In particular, the pattern-based method is one of the most important and widely studied sequence classification methods in …
New NHCAs improve multi-category classification efficiency.
Classification outperforms regression in portfolio construction, yielding higher Sharpe ratios.
C-HMCNN(h) improves HMC classification by leveraging class hierarchy.
Advances few-shot classification by treating it as supervised learning and proposing new training techniques.
We study realizations of Lie algebras by vector fields. A correspondence between classification of transitive local realizations and classification of subalgebras is generalized to the case of regular local realizations. A reasonable classification problem for general realizations is rigorously formulated and an algori…
New approach improves classification guarantees by focusing on direction rather than regression risk.