A method for reducing neural network size using look-up tables.
problem Reducing memory and computational footprint of deep neural networks.
method Iteratively learns value dictionaries and assignment matrices for network weights.
result General framework for network reduction that can handle various reduction problems.
Constrained sequence codes have been widely used in modern communication and data storage systems. Sequences encoded with constrained sequence codes satisfy constraints imposed by the physical channel, hence enabling efficient and reliable transmission of coded symbols. Traditional encoding and decoding of constrained …
Faster Tsetlin Machines use clause indexing to speed inference and learning.
problem Overfitting and slow inference in Tsetlin Machines.
method Introduced a look-up table that indexes clauses based on feature falsification, enabling faster evaluation of clauses.
result Up to 15 times faster classification and three times faster learning on MNIST and Fashion-MNIST.
Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which learns a dictionary and assigns each weight to one of the dictionary's values. …
Efficient algorithm computes knot invariants quickly.
problem Computing finite type invariants efficiently for knots.
method Create look-up tables for subdiagrams indexed by dyadic intervals, then compute invariants in ildeO(n⌈2kceil) time. result Finite type invariants can be computed on an n-crossing knot in ildeO(n⌈2kceil) time, significantly faster than previous methods. A new bootstrapping method reduces key sizes and runtime in FHE.
problem Large plaintext evaluation in FHE increases bootstrapping complexity.
method New polynomial vector representation and monic monomial permutation matrices.
result Polynomial factor improvement in key size and constant factor in runtime.
We propose a differentiable sigmoid function for efficient p-value calculation in clustering.
problem Efficient and accurate p-value calculation for clustering algorithms.
method Designed a differentiable sigmoid function to approximate the Dip-p-value transformation.
result Accelerates computation and integrates well with gradient descent-based learning schemes.
Statistical properties of order-driven double-auction markets with Bid-Ask spread are investigated through the dynamical quantities such as response function. We first attempt to utilize the so-called {\it Madhavan-Richardson-Roomans model} (MRR for short) to simulate the stochastic process of the price-change in empir…
We present a novel method for neural network quantization that emulates a non-uniform k-quantile quantizer, which adapts to the distribution of the quantized parameters. Our approach provides a novel alternative to the existing uniform quantization techniques for neural networks. We suggest to compare the results as …
We consider the use of look-up tables (LUT) to simplify the hardware implementation of a deep learning network for inferencing after weights have been successfully trained. The use of LUT replaces the matrix multiply and add operations with a small number of LUTs and addition operations resulting in a completely multip…
Paper proposes a log-domain training method to reduce neural network complexity.
problem High computational complexity in training deep neural networks limits real-time training.
method End-to-end training and inference scheme using approximate logarithmic operations in the log-domain.
result 16-bit log-based training achieves within 1% accuracy of floating-point baselines.
We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function TanH for Deep Learning. K-TanH consists of parameterized low-precision integer operations, such as, shift and add/subtract (no floating point operation needed) where parameters are stored in very small look-up t…
This work improves chemistry modeling by jointly learning reaction progress variables and look-up models.
problem Jointly modeling turbulent combustion requires solving both chemistry and flow systems simultaneously, which is computationally expensive.
method Developed a deep neural network architecture that jointly learns reaction progress variables and look-up models, improving accuracy.
result Joint learning yields more accurate results in chemistry modeling.
FleXOR trains fractional quantization for neural networks, improving accuracy and size.
problem Quantization limits to integer bits restricts compression and accuracy.
method Encryption algorithm with XOR gates for fractional bits during inference.
result FleXOR achieves high accuracy with fractional sub-1-bit weights.
Generative approach speeds hyperparameter tuning for machine learning models.
problem Computational infeasibility of cross-validation and difficulty of fully Bayesian hyper-parameter learning.
method Combines optimization-based approximations and amortization techniques.
result Rapid evaluation of hyper-parameters over grids or ranges, supporting predictive tuning and uncertainty quantification.
We consider machine learning techniques to develop low-latency approximate solutions to a class of inverse problems. More precisely, we use a probabilistic approach for the problem of recovering sparse stochastic signals that are members of the ℓp-balls. In this context, we analyze the Bayesian mean-square-error …
Bayesian reflex models AI learning like the autonomic nervous system.
problem Online learning in dynamic AI environments.
method Bayesian online algorithms with belief maintenance, sequential updating, and uncertainty-driven action balancing.
result Unified framework for adaptive AI learning.
PoET-BiN reduces power consumption in neural networks on embedded devices.
problem Power inefficiency in neural network implementations on embedded platforms.
method Look-Up Table based implementation with a modified Decision Tree approach.
result Near state-of-the-art results with up to 6 orders of magnitude energy reduction.
Revisit Fenn's table theorem from a differential-topological perspective.
problem Prove zero-existence theorem on a cylinder and horizontal square-table theorem under Fenn's boundary conditions.
method Differential-topological approach.
result Prove horizontal square-table theorem under more general boundary conditions.
The paper investigates ethical issues in large image datasets, focusing on pornographic content.
problem Ethical issues in large-scale computer vision datasets, particularly concerning pornographic content.
method Cross-sectional model-based quantitative census covering various factors in the ImageNet-ILSVRC-2012 dataset.
result The dataset contains verifiably pornographic images, including non-consensual and voyeuristic content.
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networ…
Study detects synthetic tabular data across different tables.
problem Detecting synthetic tabular data in varied tables.
method Four table-agnostic detectors combined with preprocessing schemes.
result Cross-table learning possible with naive preprocessing, but cross-table transfer challenging.
Proves a generalized table theorem for odd Euler characteristic surfaces.
problem Proving a generalized table theorem for surfaces with odd Euler characteristic.
method Using the square peg problem for smooth curves, the result is generalized to real valued functions on Riemannian surfaces with odd Euler characteristic.
result Proves the table conjecture for even functions on the two sphere.
CTSyn generates high-quality synthetic tabular data.
problem Challenges in generating high-quality synthetic tabular data.
method Diffusion-based generative foundation model with autoencoder and conditional latent diffusion.
result CTSyn outperforms existing table synthesizers on standard benchmarks.
Upper bounds for surface-links in the Yoshikawa table are estimated.
problem Estimating Kirby-Thompson invariants of surface-links.
method Using tri-plane diagrams and L-, L*-invariants.
result Upper bounds for surface-links in the Yoshikawa table are obtained.
This paper compiles and calculates triple point numbers for surface-links in Yoshikawa's table.
problem Determining the triple point number of surface-links in Yoshikawa's table.
method Using broken sheet diagrams, the paper compiles known triple point numbers and calculates or bounds the remaining ones.
result Compilation and calculation of triple point numbers for surface-links in Yoshikawa's table.
The paper proves geometric properties of square tables and saddle surfaces.
problem The mathematical table problem from a geometric-topological perspective.
method Geometric-topological proofs on cylinder, saddle surfaces, and level sets of Fenn graphs.
result Zero-existence theorem on a cylinder, proving Fenn's square-table theorem under different boundary conditions.
Machine learning speeds up search procedures for sorted tables.
problem Improving the speed of sorted table search procedures.
method Systematic experimental comparison of efficient implementations with learned counterparts.
result Learned data structures can significantly speed up search procedures.
Machine learning recreates the periodic table from element properties.
problem Recreating the periodic table using machine learning.
method Unsupervised machine learning with GTM for feature embedding.
result PTG autonomously generates various periodic table layouts.
Soft diamond regularizers improve deep learning performance and sparsity.
problem Improving deep learning performance and sparsity of trained weights.
method New soft diamond synaptic weight priors based on thick-tailed symmetric alpha stable probability curves.
result Soft diamond regularizers outperform state-of-the-art methods in deep learning tasks.
Method finds differential equations for integrable billiard tables.
problem Finding differential equations for integrable billiard tables.
method Introducing a method to find differential equations for functions defining tables.
result Illustrated method in three billiard systems.
Billiard trajectories and geodesics are closely related geometrically.
problem Understanding the relationship between billiard trajectories and geodesics on surfaces.
method Establishing mutual approximation results for billiard trajectories and geodesic segments on surfaces.
result For Riemannian billiard tables, there are families of fold-type surfaces such that every sequence of geodesic segments on these surfaces has a subsequence that converges to a billiard trajectory.
This document contains tables with the classification of prehomogeneous modules for reductive algebraic groups with up to two simple factors due to Sato, Kimura and many others, as well as corresponding tables of the étale modules appearing in this list, determined by the author. It is intended as a convenient referenc…
BiN normalizes financial time-series for better forecasting.
problem Non-stationarity and multimodality in financial time-series data.
method Bilinear Normalization (BiN) incorporated into TABL networks.
result BiN-TABL outperforms other normalization methods in financial forecasting.
Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their d…
Author discusses the Poincaré conjecture from 40 years ago.
problem Discussing the Poincaré conjecture from a historical perspective.
method Personal recollections and anecdotes.
result Memories of the Poincaré conjecture are vivid and detailed.
This note corrects errors in Hatcher and Oertel's table of boundary slopes of Montesinos knots which have projections with 10 or fewer crossings.
Compactness proven for isospectral Birkhoff billiard tables.
problem Proving compactness of isospectral Birkhoff billiard tables.
method Derived a hierarchical structure for integral invariants and used interpolating Hamiltonian.
result Compactness of equivalence classes of marked length isospectral Birkhoff billiard tables.
Method combines clustering and matrix completion for missing data in I/O tables.
problem Reconstructing missing entries in World Input-Output (I/O) matrices due to data collection issues.
method Hierarchical clustering and Matrix Completion with LASSO-like nuclear norm penalty.
result The method effectively predicts missing values from previous and similar countries' data.
TableQnA answers web queries about lists and superlatives from HTML tables.
problem Answer web queries about lists and superlatives from HTML tables.
method Extract intent from queries, use structure-aware matching, and train models with automatic data generation.
result Significantly higher precision and coverage for list and superlative queries.
Proposes φ-table for statistical SHAP explanations in regression models.
problem Lack of clear directional summaries, uncertainty, and fidelity in SHAP feature importance.
method SHAP importance selection, fitting a standardized linear surrogate, reporting coefficients, uncertainty, fidelity, and stability.
result Extends SHAP into a statistical global explanation with direction, uncertainty, fidelity, and stability.
An explicit solution found for maximizing/minimizing agreement in a 2x2 table.
problem Maximizing or minimizing agreement between clusterings with given marginals.
method Formal framework for several agreement measures, explicit solution for 2x2 table.
result An explicit solution for the 2x2 case.
We give a complete characterization of the relationship between the shape of a Euclidean polygon and the symbolic dynamics of its billiard flow. We prove that the only pairs of tables that can have the same bounce spectrum are right-angled tables that differ by an affine map. The main tool is a new theorem that establi…
To study embeddings of tangles in knots, we use quandle cocycle invariants. Computations are carried out for the tables of knots and tangles, to investigate which tangles may or may not embed in knots in the tables.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.
Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.
problem Discovering discrete algorithmic axioms missing in deep learning.
method Cayley-table completion as a testbed for algorithmic complexity minimization.
result Formal exact recovery bounds for Cayley-table completion.
Improved method for encoding contingency tables reduces mutual information bias.
problem Mutual information bias in measuring label similarity.
method Improved method for encoding contingency tables to reduce information cost.
result Better bound on reduced mutual information in typical use cases.
We present in this paper experiments on Table Recognition in hand-written registry books. We first explain how the problem of row and column detection is modeled, and then compare two Machine Learning approaches (Conditional Random Field and Graph Convolutional Network) for detecting these table elements. Evaluation wa…