Related papers: Universal Recurrent Event Memories for Streaming D…

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which…

Retentive Network (RetNet) represents a significant advancement in neural network architecture, offering an efficient alternative to the Transformer. While Transformers rely on self-attention to model dependencies, they suffer from high…

Event cameras are bio-inspired vision sensors that mimic retinas to asynchronously report per-pixel intensity changes rather than outputting an actual intensity image at regular intervals. This new paradigm of image sensor offers…

This paper proposes a low latency neural network architecture for event-based dense prediction tasks. Conventional architectures encode entire scene contents at a fixed rate regardless of their temporal characteristics. Instead, the…

Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the…

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. For language…

Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use…

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural…

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often time exhibit not only…

This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units. The…

Understanding the intricate operations of Recurrent Neural Networks (RNNs) mechanistically is pivotal for advancing their capabilities and applications. In this pursuit, we propose the Episodic Memory Theory (EMT), illustrating that RNNs…

Dominant sequence models like the Transformer represent structure implicitly through dense attention weights, incurring quadratic complexity. We propose RewriteNets, a novel neural architecture built on an alternative paradigm: explicit,…

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

During the last years, there has been a lot of interest in achieving some kind of complex reasoning using deep neural networks. To do that, models like Memory Networks (MemNNs) have combined external memory storages and attention…

Multivariate time series forecasting is extensively studied throughout the years with ubiquitous applications in areas such as finance, traffic, environment, etc. Still, concerns have been raised on traditional methods for incapable of…

Traffic forecasting is a challenging problem due to complex road networks and sudden speed changes caused by various events on roads. A number of models have been proposed to solve this challenging problem with a focus on learning…

Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We…

Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using…

We introduce RelNet: a new model for relational reasoning. RelNet is a memory augmented neural network which models entities as abstract memory slots and is equipped with an additional relational memory which models relations between all…