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.
DNAS disentangles neural architecture search for better interpretability and performance.
Bayesian optimisation with graph kernels improves neural architecture search and provides interpretability.
BINAS improves neural architecture search with interpretable models.
New architectures improve KANs, making them more interpretable and accurate.
Dual neural network architecture improves accuracy and interpretability.
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…
TINs use neural networks to interpret technical indicators for trading.
Intelligent Momentum Transformer outperforms traditional trading strategies.
TIME network simplifies complex physical processes with interpretable models.
Law explains how deep networks separate data for classification.
This work begins by establishing a mathematical formalization between different geometrical interpretations of Neural Networks, providing a first contribution. From this starting point, a new interpretation is explored, using the idea of implicit vector fields moving data as particles in a flow. A new architecture, Vec…
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been s…
Lower bound for VAE training objective for binary data.
New deep learning model interprets tabular data with variable selection and explainability.
In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art pe…
We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient learning and testing but more importantly better interpretability and trainability. We…
The study designs inherently interpretable machine learning models for high-risk sectors.
HFNO enhances interpretability of turbulent flows through parallel wavenumber bin processing.
We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties, being interpretable, applicable withou…
New definition of interpretability makes model design more actionable.
DCIts interprets complex time series data with interpretable coefficients.
In the past few years, there are several researches on Parkinson's disease (PD) recognition using single-photon emission computed tomography (SPECT) images with deep learning (DL) approach. However, the DL model's complexity usually results in difficult model interpretation when used in clinical. Even though there are …
Graph neural nets improve discrete choice modeling with network effects.
Proposes PRMs for interpreting financial risk concept drift.
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding al…
Enhances KANs for accuracy and interpretability with multi-exit architecture.
Paper interprets ResNets via gate-network controls and deep-layer classifications.
IANN visualizes all input variables effects simultaneously.
Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can reduce costs and decrease time to model deployment. Neural architecture search (NAS)…
C2G-Net improves image classification of similar objects like cells.
In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambiguous evidence. The problem of interpretation is well matched to an early and often overlooked architecture, the attractor network---a recur…
Linear attention in Transformers can be interpreted as dynamic VAR models.
NDM incorporates geometric structure into neural networks for better optimization and interpretability.
Proposes a neural network for contextual regression.
V-HMN integrates memory mechanisms for improved image recognition.
This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where interpretation of features is considered very important. The proposed approach is based on Wi…
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined. The implicit framework greatly simplifies the notation of deep learni…
In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the optimization problem for sparse nonnegative matrix factorization (NMF) of spectrograms.…
Whereas deep neural network (DNN) is increasingly applied to choice analysis, it is challenging to reconcile domain-specific behavioral knowledge with generic-purpose DNN, to improve DNN's interpretability and predictive power, and to identify effective regularization methods for specific tasks. This study designs a pa…
Classification of jets with deep learning has gained significant attention in recent times. However, the performance of deep neural networks is often achieved at the cost of interpretability. Here we propose an interpretable network trained on the jet spectrum which is a two-point correlation function of the…
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient fea…
Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design architectures to suit it. As such, architectures that fit the structure of genomics should …
A novel GP architecture, Thin and Deep GP, learns lower-dimensional representations without losing interpretability.
In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs. In order to prove the hy…
Machine learning and deep learning have gained popularity and achieved immense success in Drug discovery in recent decades. Historically, machine learning and deep learning models were trained on either structural data or chemical properties by separated model. In this study, we proposed an architecture training simult…
Mathematical study shows post-hoc explanations are better than attention weights alone.
BDH model learns like the brain, rivaling Transformer performance.