Related papers: Late Breaking Results: Conversion of Neural Networ…

Edge computing for neural networks is getting important especially for low power applications and offline devices. TensorFlow Lite and PyTorch Mobile were released for this purpose. But they mainly support mobile devices instead of…

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence. Microcontrollers (MCUs) are an attractive platform for building smart devices due to their low cost, wide availability,…

Edge computing has emerged as a popular paradigm for running latency-sensitive applications due to its ability to offer lower network latencies to end-users. In this paper, we argue that despite its lower network latency, the…

FPGA-specific DNN architectures using the native LUTs as independently trainable inference operators have been shown to achieve favorable area-accuracy and energy-accuracy tradeoffs. The first work in this area, LUTNet, exhibited…

As communication protocols evolve, datacenter network utilization increases. As a result, congestion is more frequent, causing higher latency and packet loss. Combined with the increasing complexity of workloads, manual design of congestion…

Integrating first-order logic constraints (FOLCs) with neural networks is a crucial but challenging problem since it involves modeling intricate correlations to satisfy the constraints. This paper proposes a novel neural layer, LogicMP,…

Deep neural networks with large model sizes achieve state-of-the-art results for tasks in computer vision (CV) and natural language processing (NLP). However, these large-scale models are too compute- or memory-intensive for…

Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…

With the constant increase of available data in various domains, such as the Internet of Things, Social Networks or Smart Cities, it has become fundamental that agents are able to process and reason with such data in real time. Whereas…

Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have used convnets to perform vision tasks with accuracy that was…

Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high-resolution image…

In recent years, the Edge Computing (EC) paradigm has emerged as an enabling factor for developing technologies like the Internet of Things (IoT) and 5G networks, bridging the gap between Cloud Computing services and end-users, supporting…

Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services, due to their superior recognition accuracy. They are increasingly being used on mobile devices, many times just by porting large models…

Recent years have witnessed the success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the…

In this paper, we investigate neural networks applied to multiscale simulations and discuss a design of a novel deep neural network model reduction approach for multiscale problems. Due to the multiscale nature of the medium, the fine-grid…

Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample.…

As the performance of computer systems stagnates due to the end of Moore's Law, there is a need for new models that can understand and optimize the execution of general purpose code. While there is a growing body of work on using Graph…

Deep neural networks have been successfully deployed in a wide variety of applications including computer vision and speech recognition. However, computational and storage complexity of these models has forced the majority of computations…

AI-powered edge devices currently lack the ability to adapt their embedded inference models to the ever-changing environment. To tackle this issue, Continual Learning (CL) strategies aim at incrementally improving the decision capabilities…