English
Related papers

Related papers: Power efficient ReLU design for neuromorphic compu…

200 papers

We propose spin transfer torque--magnetoresistive random access memory (STT-MRAM) based on magneto-resistance and spin transfer torque physics of band-pass spin filtering. Utilizing the electronic analogs of optical phenomena such as…

Mesoscale and Nanoscale Physics · Physics 2019-08-20 Abhishek Sharma , Ashwin Tulapurkar , Bhaskaran Muralidharan

As process technology continues to scale aggressively, circuit aging in a neuromorphic hardware due to negative bias temperature instability (NBTI) and time-dependent dielectric breakdown (TDDB) is becoming a critical reliability issue and…

Neural and Evolutionary Computing · Computer Science 2020-06-11 Shihao Song , Anup Das , Nagarajan Kandasamy

Ensuring high performance, while meeting the power budget is a challenging task as the world is moving towards next-generation computing. Researchers and designers are in search of new solutions for efficient computation. Spintronics…

Applied Physics · Physics 2022-08-31 Jagadish Rajpoot , Ravneet Paul , Shivam Verma

The loss surfaces of deep neural networks have been the subject of several studies, theoretical and experimental, over the last few years. One strand of work considers the complexity, in the sense of local optima, of high dimensional random…

One essential feature in MRAM cells is the spin torque efficiency, which describes the ratio of the critical switching current to the energy barrier. Within this paper it is reported that the spin torque efficiency can be improved by a…

Computational Physics · Physics 2017-08-02 Dieter Suess , Christoph Vogler , Florian Bruckner , Hossein Sepehri-Amin , Claas Abert

In this paper, we introduce a novel type of Rectified Linear Unit (ReLU), called a Dual Rectified Linear Unit (DReLU). A DReLU, which comes with an unbounded positive and negative image, can be used as a drop-in replacement for a tanh…

Computation and Language · Computer Science 2019-03-01 Fréderic Godin , Jonas Degrave , Joni Dambre , Wesley De Neve

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Les Atlas , Nicholas Rasmussen , Felix Schwock , Mert Pilanci

All Spin Logic gates employ multiple nano-magnets interacting through spin-torque using non-magnetic channels. Compactness, non-volatility and ultra-low voltage operation are some of the attractive features of ASL, while, low…

Mesoscale and Nanoscale Physics · Physics 2013-08-13 Mrigank Sharad , Karthik Yogendra , Arun Gaud , Kon-Woo Kwon , Kaushik Roy

Smart material implication (SIMPLY) logic has been recently proposed for the design of energy-efficient Logic-in-Memory (LIM) architectures based on non-volatile resistive memory devices. The SIMPLY logic is enabled by adding a comparator…

Emerging Technologies · Computer Science 2022-06-01 Raffaele De Rose , Tommaso Zanotti , Francesco Maria Puglisi , Felice Crupi , Paolo Pavan , Marco Lanuzza

The activation function is at the heart of a deep neural networks nonlinearity; the choice of the function has great impact on the success of training. Currently, many practitioners prefer the Rectified Linear Unit (ReLU) due to its…

Machine Learning · Computer Science 2021-08-24 Jordan Inturrisi , Sui Yang Khoo , Abbas Kouzani , Riccardo Pagliarella

In recent years the field of neuromorphic low-power systems that consume orders of magnitude less power gained significant momentum. However, their wider use is still hindered by the lack of algorithms that can harness the strengths of such…

Neural and Evolutionary Computing · Computer Science 2016-01-19 Peter U. Diehl , Guido Zarrella , Andrew Cassidy , Bruno U. Pedroni , Emre Neftci

Electrical currents in a magnetic insulator/heavy metal heterostructure can induce two simultaneous effects, namely, spin Hall magnetoresistance (SMR) on the heavy metal side and spin-orbit torques (SOTs) on the magnetic insulator side.…

Neural processing systems typically represent data using leaky integrate and fire (LIF) neuron models that generate spikes or pulse trains at a rate proportional to their input amplitudes. This mechanism requires high firing rates when…

Emerging Technologies · Computer Science 2019-05-07 Manu V Nair , Giacomo Indiveri

Activation Functions introduce non-linearity in the deep neural networks. This nonlinearity helps the neural networks learn faster and efficiently from the dataset. In deep learning, many activation functions are developed and used based on…

Machine Learning · Computer Science 2025-09-29 Ravin Kumar

We formalize and interpret the geometric structure of $d$-dimensional fully connected ReLU layers in neural networks. The parameters of a ReLU layer induce a natural partition of the input domain, such that the ReLU layer can be…

Machine Learning · Computer Science 2023-11-09 Jonatan Vallin , Karl Larsson , Mats G. Larson

Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as…

Machine Learning · Computer Science 2016-07-20 Wenling Shang , Kihyuk Sohn , Diogo Almeida , Honglak Lee

Electrical manipulation of magnetization by spin-orbit torque (SOT) has shown promise for realizing reliable magnetic memories and oscillators. To date, the generation of transverse spin current and SOT, whether it is of spin Hall effect…

Materials Science · Physics 2019-02-20 Yong-Chang Lau , Hwachol Lee , Kohji Nakamura , Masamitsu Hayashi

The phenomenon of Spin Hall Effect (SHE) generates a pure spin current transverse to an applied current in materials with strong spin-orbit coupling, although not detectable through conventional electrical measurement. An intuitive Hall…

Mesoscale and Nanoscale Physics · Physics 2024-04-08 Soumik Aon , Abu Bakkar Miah , Arpita Mandal , Harekrishna Bhunia , Dhananjaya Mahapatra , Partha Mitra

SWIN transformer is a prominent vision transformer model that has state-of-the-art accuracy in image classification tasks. Despite this success, its unique architecture causes slower inference compared with similar deep neural networks.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Mohammadreza Tayaranian , Seyyed Hasan Mozafari , James J. Clark , Brett Meyer , Warren Gross

Activation functions are widely used in neural networks to decide the activation value of the neural unit based upon linear combinations of the weighted inputs. The effective implementation of activation function is highly important, as…

Emerging Technologies · Computer Science 2019-08-28 Nursultan Kaiyrbekov , Olga Krestinskaya , Alex Pappachen James