Related papers: Transformers are Stateless Differentiable Neural C…
While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…
Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…
Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP). Inspired by such significant achievements, some pioneering works have recently been done on employing…
The capacity of a state-dependent discrete memoryless channel (SD-DMC) is derived for the setting where a message-cognizant rate-limited helper observes the state sequence noncausally, produces its description, and provides the description…
We propose a causal interpretation of self-attention in the Transformer neural network architecture. We interpret self-attention as a mechanism that estimates a structural equation model for a given input sequence of symbols (tokens). The…
Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that…
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…
This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…
Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…
Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from…
Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…
Transformers models have become the backbone of the current state-of-the-art models in language, vision, and multimodal domains. These models, at their core, utilize multi-head self-attention to selectively aggregate context, generating…
The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks. An analysis of its internal activation patterns reveals three problems: Most importantly, the lack of key-value separation makes the address…
In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and…
Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…
Deep learning (DL) is characterised by its dynamic nature, with new deep neural network (DNN) architectures and approaches emerging every few years, driving the field's advancement. At the same time, the ever-increasing use of mobile…
Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…