Related papers: SCoTTi: Save Computation at Training Time with an …

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible…

Computing at the edge is increasingly important since a massive amount of data is generated. This poses challenges in transporting all that data to the remote data centers and cloud, where they can be processed and analyzed. On the other…

Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes particularly challenging when data samples are insufficient,…

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training…

To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded to the edge for processing by an accurate but…

Prior studies have shown that the retention time of the non-volatile spin-transfer torque RAM (STT-RAM) can be relaxed in order to reduce STT-RAM's write energy and latency. However, since different applications may require different…

The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation…

In particular, large-scale deep learning and artificial intelligence model training uses a lot of computational power and energy, so it poses serious sustainability issues. The fast rise in model complexity has resulted in exponential…

We study the problem of structured prediction under test-time budget constraints. We propose a novel approach applicable to a wide range of structured prediction problems in computer vision and natural language processing. Our approach…

With the rapid advancement of large models and mobile edge computing, transfer learning, particularly through fine-tuning, has become crucial for adapting models to downstream tasks. Traditionally, this requires users to share their data…

Ensuring energy-efficient design in neuromorphic computing systems necessitates a tailored architecture combined with algorithmic approaches. This manuscript focuses on enhancing brain-inspired perceptual computing machines through a novel…

On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques. Typically, these models are pretrained on large GPU clusters and have enough parameters to generalise across…

Edge computing is the natural progression from Cloud computing, where, instead of collecting all data and processing it centrally, like in a cloud computing environment, we distribute the computing power and try to do as much processing as…

Self-training based semi-supervised learning algorithms have enabled the learning of highly accurate deep neural networks, using only a fraction of labeled data. However, the majority of work on self-training has focused on the objective of…

As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile…

Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have…

The paradigm of pre-training and fine-tuning has laid the foundation for deploying deep learning models. However, most fine-tuning methods are designed to meet a specific resource budget. Recently, considering diverse deployment scenarios…

Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple…

Training a machine learning model is both compute and data-intensive. Most of the model training is performed on high performance compute nodes and the training data is stored near these nodes for faster training. But there is a growing…

This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…