Related papers: A bi-directional Address-Event transceiver block f…
This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR systems. AMD performs parallel NAR inference within contiguous blocks…
Most of today's communication systems are designed to target reliable message recovery after receiving the entire encoded message (codeword). However, in many practical scenarios, the transmission process may be interrupted before receiving…
Data streaming transmission over a block fading channel is studied. It is assumed that the transmitter receives a new message at each channel block at a constant rate, which is fixed by an underlying application, and tries to deliver the…
Deep Learning (DL) training platforms are built by interconnecting multiple DL accelerators (e.g., GPU/TPU) via fast, customized interconnects with 100s of gigabytes (GBs) of bandwidth. However, as we identify in this work, driving this…
Analog In-Memory Computing (AIMC) is emerging as a disruptive paradigm for heterogeneous computing, potentially delivering orders of magnitude better peak performance and efficiency over traditional digital signal processing architectures…
In communication systems, Autoencoder (AE) refers to the concept of replacing parts of the transmitter and receiver by artificial neural networks (ANNs) to train the system end-to-end over a channel model. This approach aims to improve…
This paper presents a TDMA based energy efficient cognitive radio multichannel medium access control (MAC) protocol called ECR-MAC for wireless Ad Hoc Networks. ECR-MAC requires only a single half-duplex radio transceiver on each node that…
Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neural networks (SNNs) offers an attractive path, but practical deployment on resource-constrained…
The rapid advancement of embedded multicore and many-core systems has revolutionized computing, enabling the development of high-performance, energy-efficient solutions for a wide range of applications. As models scale up in size, data…
Recently, practical brain-computer interface is actively carried out, especially, in an ambulatory environment. However, the electroencephalography (EEG) signals are distorted by movement artifacts and electromyography signals when users…
End-to-end event-based computation has the potential to push the envelope in latency and energy efficiency for edge AI applications. Unfortunately, event-based sensors (e.g., DVS cameras) and neuromorphic spike-based processors (e.g.,…
The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-cases, the system must be able to decode utterances in a…
Large-scale graph processing has drawn great attention in recent years. Most of the modern-day datacenter workloads can be represented in the form of Graph Processing such as MapReduce etc. Consequently, a lot of designs for Domain-Specific…
Artificial neural networks and computational neuroscience models have made tremendous progress, allowing computers to achieve impressive results in artificial intelligence (AI) applications, such as image recognition, natural language…
The demands for high data rates in 6G networks have driven the transition toward higher frequencies and larger antenna apertures, giving rise to the near-field communications. In the near-field region, spherical waves enable beam focusing…
Electronic Health Records (EHRs) contain rich, longitudinal patient information across structured (e.g., labs, vitals, and imaging) and unstructured (e.g., clinical notes) modalities. While deep learning models such as RNNs and Transformers…
In modern communication systems with feedback, there are increasingly more scenarios where the transmitter has much less power than the receiver (e.g., medical implant devices), which we refer to as noise-asymmetric channels. For such…
This paper focuses on wireless energy transfer (WET) to a pair of low complex energy receivers (ER), by only utilizing received signal strength indicator (RSSI) values that are fed back from the ERs to the energy transmitter (ET). Selecting…
In this paper, we consider a prospective receiving hybrid beamforming structure consisting of several radio frequency (RF) chains and abundant antenna elements in multi-input multi-output (MIMO) systems. Due to conventional costly full…
We generalize an existing low-cost analog signal processing concept that takes advantage of the periodicity of vehicle-to-vehicle broadcast service to the transmitter side. In particular, we propose to process multiple antennas using either…