Related papers: Information Aggregation via Dynamic Routing for Se…
Recurrent Neural Networks (RNN) received a vast amount of attention last decade. Recently, the architectures of Recurrent AutoEncoders (RAE) found many applications in practice. RAE can extract the semantically valuable information, called…
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs. The mainstream approaches for runtime acceleration consist in pruning connections (unstructured pruning)…
Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause of this limitation stems from the Semantic Entanglement…
Time, cost, and energy efficiency are critical considerations in Deep-Learning (DL), particularly when processing long texts. Transformers, which represent the current state of the art, exhibit quadratic computational complexity relative to…
Vector averaging remains one of the most popular sentence embedding methods in spite of its obvious disregard for syntactic structure. While more complex sequential or convolutional networks potentially yield superior classification…
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information.…
The fast growing scale and heterogeneity of current communication networks necessitate the design of distributed cross-layer optimization algorithms. So far, the standard approach of distributed cross-layer design is based on dual…
Despite technological advancements, the significance of interdisciplinary subjects like complex networks has grown. Exploring communication within these networks is crucial, with traffic becoming a key concern due to the expanding…
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…
Controlling and coordinating urban traffic flow through robot vehicles is emerging as a novel transportation paradigm for the future. While this approach garners growing attention from researchers and practitioners, effectively managing and…
In this paper, we propose a methodology to compute the optimal finite-length coding rate for random linear network coding schemes over a line network. To do so, we first model the encoding, reencoding, and decoding process of different…
The increasing popularity of deep neural network (DNN) applications demands high computing power and efficient hardware accelerator architecture. DNN accelerators use a large number of processing elements (PEs) and on-chip memory for…
Automatically identifying data types of web structured data is a key step in the process of web data integration. Web structured data is usually associated with entities or objects in a particular domain. In this paper, we aim to map…
In this work, an eavesdropping-aware routing and spectrum allocation approach is proposed utilizing network coding (NC) in elastic optical networks (EONs). To provide physical layer security in EONs and secure the confidential connections…
Network embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension -- small enough to be efficient and large enough to be…
Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning…
While routing in wireless networks has been studied extensively, existing protocols are typically designed for a specific set of network conditions and so cannot accommodate any drastic changes in those conditions. For instance, protocols…
We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text generation works that require re-encoding of the context after…
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To…
Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word…