Related papers: Towards Tensor Network Models for Low-Latency Jet …
We compare the performance of a convolutional neural network (CNN) trained on jet images with dense neural networks (DNNs) trained on n-subjettiness variables to study the distinguishing power of these two separate techniques applied to top…
We study tensor networks as a model of arithmetic computation for evaluating multilinear maps. These capture any algorithm based on low border rank tensor decompositions, such as $O(n^{\omega+\epsilon})$ time matrix multiplication, and in…
The High-Luminosity LHC (HL-LHC) will reach luminosities up to 7 times higher than the previous run, yielding denser events and larger occupancies. Next generation trigger algorithms must retain reliable selection within a strict latency…
Single computation engines have become a popular design choice for FPGA-based convolutional neural networks (CNNs) enabling the deployment of diverse models without fabric reconfiguration. This flexibility, however, often comes with…
Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU…
Tensor networks are a compressed format for multi-dimensional data. One-dimensional tensor networks -- often referred to as tensor trains (TT) or matrix product states (MPS) -- are increasingly being used as a numerical ansatz for continuum…
We present an algorithm for supervised learning using tensor networks, employing a step of preprocessing the data by coarse-graining through a sequence of wavelet transformations. We represent these transformations as a set of tensor…
This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex,…
Logic Tensor Networks (LTN) is a Neuro-Symbolic framework that effectively incorporates deep learning and logical reasoning. In particular, LTN allows defining a logical knowledge base and using it as the objective of a neural model. This…
Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…
Graph classification is an important learning task for graph-structured data. Graph neural networks (GNNs) have recently gained growing attention in graph learning and have shown significant improvements in many important graph problems.…
Deploying Large Language Models (LLMs) efficiently on edge devices is often constrained by limited memory capacity and high power consumption. Low-bit quantization methods, particularly ternary quantization, have demonstrated significant…
Tensor Network methods have been established as a powerful technique for simulating low dimensional strongly-correlated systems for over two decades. Employing the formalism of Matrix Product States, we investigate the phase diagram of the…
Tensor train (TT) decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. However, since the tensor product is not commutative, permutation of…
Temporal Neural Networks (TNNs) are spiking neural networks that use time as a resource to represent and process information, similar to the mammalian neocortex. In contrast to compute-intensive deep neural networks that employ separate…
Neural networks have achieved state of the art results in many areas, supposedly due to parameter sharing, locality, and depth. Tensor networks (TNs) are linear algebraic representations of quantum many-body states based on their…
Hybrid Tensor Networks (hTN) offer a promising solution for encoding variational quantum states beyond the capabilities of efficient classical methods or noisy quantum computers alone. However, their practical usefulness and many…
Semantic image interpretation can vastly benefit from approaches that combine sub-symbolic distributed representation learning with the capability to reason at a higher level of abstraction. Logic Tensor Networks (LTNs) are a class of…
High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns. However, this high dimensionality also introduces…
Tree tensor network states (TTNS) decompose the system wavefunction to the product of low-rank tensors based on the tree topology, serving as the foundation of the multi-layer multi-configuration time-dependent Hartree (ML-MCTDH) method. In…