arXiv research

We prove that a topological manifold (possibly with boundary) admitting a continuous cancellative binary operation is orientable. This implies that the Möbius band admits no cancellative continuous binary operation. This answers a question posed by the second author in 2010.

In this paper we study Thurston's automaton on the braid groups via binary operations. These binary operations are obtained from the construction of this automaton. We study these operations and find some connections between them in a "skew lattice" spirit.

We use mathematical induction to prove that the horizontal composition in the class of coherently diagonal complexes is indeed a binary operation. That is to say, the embedding of two coherently diagonal complexes in an alternating planar diagram produces a coherently diagonal complex.

We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bit…

Modified Metropolis algorithm ensures convergence for multivariate binary distributions with fixed-order updates.

This paper presents an efficient binarized algorithm for both learning and classification of human epileptic seizures from intracranial electroencephalography (iEEG). The algorithm combines local binary patterns with brain-inspired hyperdimensional computing to enable end-to-end learning and inference with binary opera…

We consider the $\mathfrak{aff}(n|1)-$module structure on the spaces of differential bilinear operators acting on the superspaces of weighted densities. We classify $\mathfrak{aff}(n|1)-$invariant binary differential operators acting on the spaces of weighted densities. This result allows us to compute the first $\math…

Binary operations on algebras of observables are studied in the quantum as well as in the classical case. It is shown that certain natural compatibility conditions with the associative product imply the properties which usually are additionally required. In particular, it is proved that locality of a Loday bracket on s…

Over the $(1,n)$-dimensional real superspace, $n>1$, we classify $\mathcal{K}(n)$-invariant binary differential operators acting on the superspaces of weighted densities, where $\mathcal{K}(n)$ is the Lie superalgebra of contact vector fields. This result allows us to compute the first differential cohomology of %the L…

Quantum machine learning model for binary classification.

Geometric analysis of ROC and PR curves for binary classification.

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during tr…

A new algebraic structure emerges from reductive homogeneous spaces.

Paper introduces Laplace-HDC for better binary hyperdimensional computing.

The paper constructs new algebraic structures from Lie algebras and ternary Nambu-Lie algebras, leading to Yang-Baxter operators.

QNNs can't distinguish binary signals from their negations, revealing a new symmetry.

Two quandles from Coxeter groups studied, showing similarities in automorphism groups.

Matrix factorization is a key tool in data analysis; its applications include recommender systems, correlation analysis, signal processing, among others. Binary matrices are a particular case which has received significant attention for over thirty years, especially within the field of data mining. Dictionary learning …

In this paper are given explicit calculations of Laplace operator spectrum for smooth real/complex-valued functions on all connected compact simple rank three Lie groups with biinvariant Riemannian metric and established a connection of obtained formulas with the number theory and integer ternary and binary quadratic f…

Modified AUC improves CNN training by considering model confidence.

We give an explicit algorithm and source code for computing optimal weights for combining a large number N of alphas. This algorithm does not cost O(N^3) or even O(N^2) operations but is much cheaper, in fact, the number of required operations scales linearly with N. We discuss how in the absence of binary or quasi-bin…

B-CP reduces knowledge graph model size by replacing real-valued embeddings with binary values.

Federated learning approach for binary matrix factorization.

We investigate constructions of higher arity self-distributive operations, and give relations between cohomology groups corresponding to operations of different arities. For this purpose we introduce the notion of mutually distributive $n$-ary operations generalizing those for the binary case, and define a cohomology t…

MeliusNet improves binary neural networks to match MobileNet-v1 accuracy.

We consider a proximal operator given by a quadratic function subject to bound constraints and give an optimization algorithm using the alternating direction method of multipliers (ADMM). The algorithm is particularly efficient to solve a collection of proximal operators that share the same quadratic form, or if the qu…

PoET-BiN reduces power consumption in neural networks on embedded devices.

Observational data hints at a finite universe, with spherical manifolds such as the Poincare dodecahedral space tentatively providing the best fit. Simulating the physics of a model universe requires knowing the eigenmodes of the Laplace operator on the space. The present article provides explicit polynomial eigenmodes…

Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms. In this paper, we propose a new method to evaluate DNNs trained with 32bit floating point (float32) accura…

We compute the spectral action of $SU(2)/Γ$ with the trivial spin structure and the round metric and find it in each case to be equal to $\frac{1}{|Γ|} (Λ^3 \hat{f}^{(2)}(0) - 1/4Λ\hat{f}(0))+ O(Λ^{-\infty})$. We do this by explicitly computing the spectrum of the Dirac operator for $SU(2)/Γ$ equipped with the trivial …

Proposes an alternative method to train RBMs with binary synapses using Bayesian learning rule.

Theory explains why DARTS favors deep architectures over shallow ones.

Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the…

LxCIM metric improves binary classification performance evaluation.

Paper proposes algorithms for BMF using integer programming.

Improves gradient estimation for discrete distributions with variance reduction techniques.

Study binary perceptrons' capacity using random duality theory.

Using the technique of higher derived brackets developed by Voronov, we construct a homotopy Loday algebra in the sense of Ammar and Poncin associated to any symplectic $2$-manifold. The algebra we obtain has a particularly nice structure, in that it accommodates the Dorfman bracket of a Courant algebroid as the binary…

In \cite{PrzytyskiTraczyk} J.H.Przytyski and P.Traczyk introduced an algebraic structure, called {\it a Conway algebra,} and constructed an invariant of oriented links, which is a generalization of the Homflypt polynomial invariant. On the other hand, in \cite{KauffmanLambropoulou} L. H. Kauffman and S. Lambropoulou in…

Binary neural networks (BNN) have been studied extensively since they run dramatically faster at lower memory and power consumption than floating-point networks, thanks to the efficiency of bit operations. However, contemporary BNNs whose weights and activations are both single bits suffer from severe accuracy degradat…

This paper uses MIL and MHCNN-RNN to predict precursors to aviation safety events.

Cryptocurrencies are ranked for efficiency using a new Complexity-Entropy Plane.

$KS$-algebra consists of expressions constructed with four kinds operations, the minimum, maximum, difference and additively homogeneous generalized means. Five families of $Z$-classifiers are investigated on binary classification tasks between English phonemes. It is shown that the classifiers are able to reflect well…

This paper introduces lattice representations for efficient discrete learning.

New algorithm optimizes AUC in binary classification and changepoint detection.

We propose a method for maximizing a partial area under a receiver operating characteristic (ROC) curve (pAUC) for binary classification tasks. In binary classification tasks, accuracy is the most commonly used as a measure of classifier performance. In some applications such as anomaly detection and diagnostic testing…

New method improves accuracy of quantized neural networks.

Introduces a differentiable approximation to the zero-one loss.