Related papers: An Improved Recursive Algorithm for V-BLAST to Sav…

As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental…

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter…

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each…

Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…

The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…

Digital computers have been getting exponentially faster for decades, but huge challenges exist today. Transistor scaling, described by Moore's law, has been slowing down over the last few years, ending the era of fully predictable…

Coherent optical memories will likely play an important role in future quantum communication networks. Among the different platforms, memories based on ladder-type orbital transitions in atomic gasses offer high bandwidth ($>100$ MHz),…

Despite the impressive search rate of one key per clock cycle, the update stage of a random-access-memory-based content-addressable-memory (RAM-based CAM) always suffers high latency. Two primary causes of such latency include: (1) the…

We introduce a new method for speeding up the inference of deep neural networks. It is somewhat inspired by the reduced-order modeling techniques for dynamical systems.The cornerstone of the proposed method is the maximum volume algorithm.…

Traditional optimization methods rely on the use of single-precision floating point arithmetic, which can be costly in terms of memory size and computing power. However, mixed precision optimization techniques leverage the use of both…

We give an overview of the theoretical results for matrix block-recursive algorithms in commutative domains and present the results of experiments that we conducted with new parallel programs based on these algorithms on a supercomputer…

This letter proposes a fast identification algorithm for Wiener-Hammerstein systems. The computational cost of separating the front and the back linear time invariant block dynamics is significantly improved by using discrete optimization.…

Non-volatile memory (NVM) technologies such as PCM, ReRAM and STT-RAM allow processors to directly write values to persistent storage at speeds that are significantly faster than previous durable media such as hard drives or SSDs. Many…

Due to the huge difference in performance between the computer memory and processor, the virtual memory management plays a vital role in system performance. A Cache memory is the fast memory which is used to compensate the speed difference…

Image restoration is typically addressed through non-convex inverse problems, which are often solved using first-order block-wise splitting methods. In this paper, we consider a general type of non-convex optimisation model that captures…

Inertial algorithms for minimizing nonsmooth and nonconvex functions as the inertial proximal alternating linearized minimization algorithm (iPALM) have demonstrated their superiority with respect to computation time over their non inertial…

Recursive Best-First Search (RBFS) is a heuristic search algorithm known for its efficient memory usage compared to traditional best-first search methods like A*. Despite its theoretical advantages, RBFS is complex and difficult to teach…

In recommendation systems, practitioners observed that increase in the number of embedding tables and their sizes often leads to significant improvement in model performances. Given this and the business importance of these models to major…

Herein, a bit-wise Convolutional Neural Network (CNN) in-memory accelerator is implemented using Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) computational sub-arrays. It utilizes a novel AND-Accumulation method capable of…

The increasing complexity of autonomous systems has driven a shift to integrated heterogeneous SoCs with real-time and safety demands. Ensuring deterministic WCETs and low-latency for critical tasks requires minimizing interference on…