Related papers: DAPA: Distribution Aware Piecewise Activation Func…

Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandwidth-constrained environments. We present ASTRA, a…

Benefiting from the self-attention mechanism, Transformer models have attained impressive contextual comprehension capabilities for lengthy texts. The requirements of high-throughput inference arise as the large language models (LLMs)…

Selecting the most suitable activation function is a critical factor in the effectiveness of deep learning models, as it influences their learning capacity, stability, and computational efficiency. In recent years, the Gaussian Error Linear…

The distributed shared memory (DSM) architecture is widely used in today's computer design to mitigate the ever-widening processing-memory gap, and inevitably exhibits non-uniform memory access (NUMA) to shared-memory parallel applications.…

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

Phase wrapping is a major problem in direction-of-arrival (DOA) estimation using phase-difference observations. For a sensor pair with an inter-sensor spacing greater than half of the wavelength ($\lambda/2$) of the signal, phase wrapping…

Next activity prediction in predictive business process monitoring is crucial for operational efficiency and informed decision-making. While machine learning and Artificial Intelligence have achieved promising results, challenges remain in…

We propose a new active learning algorithm for PDFA based on three main aspects: a congruence over states which takes into account next-symbol probability distributions, a quantization that copes with differences in distributions, and an…

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization…

Dedicated accelerators are being designed to address the huge resource requirement of the deep neural network (DNN) applications. The power, performance and area (PPA) constraints limit the number of MACs available in these accelerators.…

Existing approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as…

Computing sparse redundant representations is an important problem both in applied mathematics and neuroscience. In many applications, this problem must be solved in an energy efficient way. Here, we propose a hybrid distributed algorithm…

Six-dimensional movable antenna (6DMA) is an innovative technology to improve wireless network capacity by adjusting 3D positions and 3D rotations of antenna surfaces based on channel spatial distribution. However, the existing works on…

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and…

Domain-specialized FPGAs have delivered unprecedented performance for low-latency inference across scientific and industrial workloads, yet nearly all existing accelerators assume static models trained offline, relegating learning and…

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…

We have proposed orthogonal-Pad\'e activation functions, which are trainable activation functions and show that they have faster learning capability and improves the accuracy in standard deep learning datasets and models. Based on our…

Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and…

Human activity recognition (HAR) is a time series classification task that focuses on identifying the motion patterns from human sensor readings. Adequate data is essential but a major bottleneck for training a generalizable HAR model,…