paper-with-me

Papers

NEURAL EXECUTION ENGINES

2020-01-01 · ICLR 2020 1 · Yujun Yan, Kevin Swersky, Danai Koutra, Parthasarathy Ranganathan, Milad Hashemi

Turing complete computation and reasoning are often regarded as necessary pre- cursors to general intelligence. There has been a significant body of work studying neural networks that mimic general computation, but these networks fail to generalize to data distributions that are outside of their training set. We study this problem through the lens of fundamental computer science problems: sorting and graph processing. We modify the masking mechanism of a transformer in order to allow them to implement rudimentary functions with strong generalization. We call this model the Neural Execution Engine, and show that it learns, through supervision, to numerically compute the basic subroutines comprising these algorithms with near perfect accuracy. Moreover, it retains this level of accuracy while generalizing to unseen data and long sequences outside of the training distribution.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Benchmarking Meaning Representations in Neural Semantic Parsing

2020-11-01 · EMNLP 2020 11 · Jiaqi Guo, Qian Liu, Jian-Guang Lou, Zhenwen Li 외

Meaning representation is an important component of semantic parsing. Although researchers have designed a lot of meaning representations, recent work focuses on only a few of them. Thus, the impact of meaning representa…

BenchmarkingSemantic Parsing

Energy consumption of code small language models serving with runtime engines and execution providers

2024-12-19 · Francisco Durán, Matias Martinez, Patricia Lago, Silverio Martínez-Fernández

Background. The rapid growth of Language Models (LMs), particularly in code generation, requires substantial computational resources, raising concerns about energy consumption and environmental impact. Optimizing LMs inf…

Code GenerationCPU

Scaling Up Knowledge Graph Creation to Large and Heterogeneous Data Sources

2022-01-24 · Enrique Iglesias, Samaneh Jozashoori, Maria-Esther Vidal

RDF knowledge graphs (KG) are powerful data structures to represent factual statements created from heterogeneous data sources. KG creation is laborious and demands data management techniques to be executed efficiently. …

Knowledge GraphsManagementScheduling

A functionality taxonomy for document search engines

2021-05-27 · Rik D. T. Janssen, Henderik A. Proper

In this paper a functionality taxonomy for document search engines is proposed. It can be used to assess the features of a search engine, to position search engines relative to each other, or to select which search engin…

Minuet: Accelerating 3D Sparse Convolutions on GPUs

2023-12-01 · Jiacheng Yang, Christina Giannoula, Jun Wu, Mostafa Elhoushi 외

Sparse Convolution (SC) is widely used for processing 3D point clouds that are inherently sparse. Different from dense convolution, SC preserves the sparsity of the input point cloud by only allowing outputs to specific …

GPU