Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines

• URL: http://arxiv.org/abs/2406.02648v1
• Date: Tue, 4 Jun 2024 14:16:52 GMT
• Title: Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines
• Authors: Vojtech Halenka, Ahmed K. Kadhim, Paul F. A. Clarke, Bimal Bhattarai, Rupsa Saha, Ole-Christoffer Granmo, Lei Jiao, Per-Arne Andersen,
• Abstract summary: We propose a hypervector (HV) based method for expressing arbitrarily large sets of concepts associated with any input data. Using a hyperdimensional space to build vectors drastically expands the capacity and flexibility of the TM. We demonstrate how images, chemical compounds, and natural language text are encoded according to the proposed method, and how the resulting HV-powered TM can achieve significantly higher accuracy and faster learning.
• Score: 12.619567138333492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal spectra, chemical compounds, and natural language is not trivial. In this paper, we propose a hypervector (HV) based method for expressing arbitrarily large sets of concepts associated with any input data. Using a hyperdimensional space to build vectors drastically expands the capacity and flexibility of the TM. We demonstrate how images, chemical compounds, and natural language text are encoded according to the proposed method, and how the resulting HV-powered TM can achieve significantly higher accuracy and faster learning on well-known benchmarks. Our results open up a new research direction for TMs, namely how to expand and exploit the benefits of operating in hyperspace, including new booleanization strategies, optimization of TM inference and learning, as well as new TM applications.

Related papers

• Text-Guided Multi-Property Molecular Optimization with a Diffusion Language Model [77.50732023411811]
  We propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM) TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions. Our approach surpasses state-of-the-art methods in optimizing molecular structural similarity and enhancing chemical properties on the benchmark dataset.
  arXiv  Detail & Related papers  (2024-10-17T14:30:27Z)
• Learning local equivariant representations for quantum operators [7.747597014044332]
  We introduce a novel deep learning model, SLEM, for predicting multiple quantum operators. SLEM achieves state-of-the-art accuracy while dramatically improving computational efficiency. We demonstrate SLEM's capabilities across diverse 2D and 3D materials, achieving high accuracy even with limited training data.
  arXiv  Detail & Related papers  (2024-07-08T15:55:12Z)
• Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks [32.33355192614434]
  We propose an effective and efficient surrogate of the Transformer, called Sliceformer. Our Sliceformer replaces the classic MHA mechanism with an extremely simple slicing-sorting'' operation. Our Sliceformer achieves comparable or better performance with lower memory cost and faster speed than the Transformer and its variants.
  arXiv  Detail & Related papers  (2023-10-26T14:43:07Z)
• Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers [71.32827362323205]
  We propose a new class of linear Transformers calledLearner-Transformers (Learners) They incorporate a wide range of relative positional encoding mechanisms (RPEs) These include regular RPE techniques applied for sequential data, as well as novel RPEs operating on geometric data embedded in higher-dimensional Euclidean spaces.
  arXiv  Detail & Related papers  (2023-02-03T18:57:17Z)
• Composable Text Controls in Latent Space with ODEs [97.12426987887021]
  This paper proposes a new efficient approach for composable text operations in the compact latent space of text. By connecting pretrained LMs to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. Experiments show that composing those operators within our approach manages to generate or edit high-quality text.
  arXiv  Detail & Related papers  (2022-08-01T06:51:45Z)
• Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval [60.457378374671656]
  Tevatron is a dense retrieval toolkit optimized for efficiency, flexibility, and code simplicity. We show how Tevatron's flexible design enables easy generalization across datasets, model architectures, and accelerator platforms.
  arXiv  Detail & Related papers  (2022-03-11T05:47:45Z)
• HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters [61.354362652006834]
  HyperNP is a scalable method that allows for real-time interactive exploration of projection methods by training neural network approximations. We evaluate the performance of the HyperNP across three datasets in terms of performance and speed.
  arXiv  Detail & Related papers  (2021-06-25T17:28:14Z)
• Demystifying BERT: Implications for Accelerator Design [4.80595971865854]
  We focus on BERT, one of the most popular NLP transfer learning algorithms, to identify how its algorithmic behavior can guide future accelerator design. We characterize compute-intensive BERT computations and discuss software and possible hardware mechanisms to further optimize these computations. Overall, our analysis identifies holistic solutions to optimize systems for BERT-like models.
  arXiv  Detail & Related papers  (2021-04-14T01:06:49Z)
• Multilinear Compressive Learning with Prior Knowledge [106.12874293597754]
  Multilinear Compressive Learning (MCL) framework combines Multilinear Compressive Sensing and Machine Learning into an end-to-end system. Key idea behind MCL is the assumption of the existence of a tensor subspace which can capture the essential features from the signal for the downstream learning task. In this paper, we propose a novel solution to address both of the aforementioned requirements, i.e., How to find those tensor subspaces in which the signals of interest are highly separable?
  arXiv  Detail & Related papers  (2020-02-17T19:06:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.