paper-with-me

Papers

Do Transformers Need Deep Long-Range Memory

2020-07-07 · Jack W. Rae, Ali Razavi

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL -- a Transformer augmented with a long-range memory of past activations -- has been shown to be state-of-the-art across a variety of well-studied benchmarks. The Transformer-XL incorporates a long-range memory at every layer of the network, which renders its state to be thousands of times larger than RNN predecessors. However it is unclear whether this is necessary. We perform a set of interventions to show that comparable performance can be obtained with 6X fewer long range memories and better performance can be obtained by limiting the range of attention in lower layers of the network.

📄 PDF Abstract BibTeX arXiv:2007.03356

Code (1)

lucidrains/memorizing-transformers-pytorch pytorch

Tasks

Deep AttentionLanguage Modelling

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
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Do Transformers Need Deep Long-Range Memory?

2020-07-01 · ACL 2020 6 · Jack Rae, Ali Razavi

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL {---} a Transformer augmented with a long-range memory of past activation…

Deep AttentionLanguage Modelling

Blockwise Parallel Transformers for Large Context Models

2023-09-21 · NeurIPS 2023 11

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the sel…

Logarithmic Memory Networks (LMNs): Efficient Long-Range Sequence Modeling for Resource-Constrained Environments

2025-01-14 · Mohamed A. Taha

Long-range sequence modeling is a crucial aspect of natural language processing and time series analysis. However, traditional models like Recurrent Neural Networks (RNNs) and Transformers suffer from computational and m…

Time Series Analysis

Memformer: A Memory-Augmented Transformer for Sequence Modeling

2020-10-14 · Qingyang Wu, Zhenzhong Lan, Kun Qian, Jing Gu 외

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an effici…

Efficient Neural NetworkLanguage Modelling

Memformer: A Memory-Augmented Transformer for Sequence Modeling

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an effici…

Efficient Neural Network