Related papers: Associative Memory For Reversible Programming and …
Development of large computerized systems requires both combinational and sequential circuits. Registers and counters are two important examples of sequential circuits, which are widely used in practical applications like CPUs. The basic…
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…
Recent advances in neuroscience together with nanoscale electronic device technology have resulted in huge interests in realizing brain-like computing hardwares using emerging nanoscale memory devices as synaptic elements. Although there…
The Entropic Associative Memory holds objects in a 2D relation or ``memory plane'' using a finite table as the medium. Memory objects are stored by reinforcing simultaneously the cells used by the cue, implementing a form of Hebb's learning…
In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…
The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time.…
Performance modeling of parallel applications on multicore computers remains a challenge in computational co-design due to the complex design of multicore processors including private and shared memory hierarchies. We present a Scalable…
Several guiding principles for thought processes are proposed and a neural-network-type model implementing these principles is presented and studied. We suggest to consider thinking within an associative network built-up of overlapping…
Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…
This work proposes a switched model reference adaptive control (S-MRAC) architecture for a multi-input multi-output (MIMO) switched linear system with memory for enhanced learning. A salient feature of the proposed method that separates it…
Spin-glass models of associative memories are a cornerstone between statistical physics and theoretical neuroscience. In these networks, stochastic spin-like units interact through a synaptic matrix shaped by local Hebbian learning. In…
Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed…
Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and…
In our earlier work [Appl. Phys. Lett. 92, 022509 (2008)], we proposed nonvolatile vortex random access memory (VRAM) based on the energetically stable twofold ground state of vortex-core magnetizations as information carrier. Here we…
Transformers excel through content-addressable retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative memory at the level of probability measures, treating a context as a distribution over…
In-memory computing with resistive crossbar arrays has been suggested to accelerate deep-learning workloads in highly efficient manner. To unleash the full potential of in-memory computing, it is desirable to accelerate the training as well…
In this work, we propose "TimeFloats," an efficient train-in-memory architecture that performs 8-bit floating-point scalar product operations in the time domain. While building on the compute-in-memory paradigm's integrated storage and…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
A programmable linear resistor with a compact footprint would have profound implications for microelectronics, enabling efficient in-sensor analog signal processing and in-memory computing. Non-volatile memory offers a potential solution…
We propose an Ising machine made of microelectromechanical systems (MEMS), where the annealing process is automatically executed by a dissipation mechanism. The core structure is a series of buckled plates. Two stable positions of each…