Related papers: A Low-Footprint Class Loading Mechanism for Embedd…
In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…
Battery-less technology evolved to replace battery technology. Non-volatile memory (NVM) based processors were explored to store the program state during a power failure. The energy stored in a capacitor is used for a backup during a power…
In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…
Transformers provide promising accuracy and have become popular and used in various domains such as natural language processing and computer vision. However, due to their massive number of model parameters, memory and computation…
Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…
The article investigates the relationship between time complexity and energy consumption in sorting algorithms, focusing on commonly-used algorithms implemented in Java: Bubble Sort, Counting Sort, Merge Sort, and Quick Sort. The…
Current HPC systems provide memory resources that are statically configured and tightly coupled with compute nodes. However, workloads on HPC systems are evolving. Diverse workloads lead to a need for configurable memory resources to…
Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their use in many applications, especially those that depend on…
While the advanced machine learning algorithms are effective in load forecasting, they often suffer from low data utilization, and hence their superior performance relies on massive datasets. This motivates us to design machine learning…
This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classes and a…
We use simulation to estimate the steady-state performance of a stable multiclass queueing network. Standard estimators have been seen to perform poorly when the network is heavily loaded. We introduce two new simulation estimators. The…
Software reuse may result in software bloat when significant portions of application dependencies are effectively unused. Several tools exist to remove unused (byte)code from an application or its dependencies, thus producing smaller…
Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies.…
On-device learning has emerged as a promising direction for AI development, particularly because of its potential to reduce latency issues and mitigate privacy risks associated with device-server communication, while improving energy…
Virtualization is a key building block of next-generation mobile networks. It can be implemented through two main approaches: traditional virtual machines and lighter-weight containers. Our objective in this paper is to compare these…
We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…
Prices of NAND flash memories are falling drastically due to market growth and fabrication process mastering while research efforts from a technological point of view in terms of endurance and density are very active. NAND flash memories…
Embedded system software is highly constrained from performance, memory footprint, energy consumption and implementing cost view point. It is always desirable to obtain better Instructions per Cycle. Instruction cache has major contribution…
Recently Java programming environment has become so popular. Java programming language is a language that is designed to be portable enough to be executed in wide range of computers ranging from cell phones to supercomputers. Computer…
Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…