145 citations · 981 across the 31 of their papers we have counts for
6 papers · 1 filter
Fast offset corrected in-memory training
Malte J. Rasch, Fabio Carta, Omebayode Fagbohungbe +1
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 c…
Neural Network Training with Asymmetric Crosspoint Elements
Murat Onen, Tayfun Gokmen, Teodor K. Todorov +5
Analog crossbar arrays comprising programmable nonvolatile resistors are under intense investigation for acceleration of deep neural network training. However, the ubiquitous asymm…
A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays
Malte J. Rasch, Diego Moreda, Tayfun Gokmen +6
We introduce the IBM Analog Hardware Acceleration Kit, a new and first of a kind open source toolkit to simulate analog crossbar arrays in a convenient fashion from within PyTorch…
Algorithm for Training Neural Networks on Resistive Device Arrays
Tayfun Gokmen, Wilfried Haensch
Hardware architectures composed of resistive cross-point device arrays can provide significant power and speed benefits for deep neural network training workloads using stochastic…
Training LSTM Networks with Resistive Cross-Point Devices
Tayfun Gokmen, Malte Rasch, Wilfried Haensch
In our previous work we have shown that resistive cross point devices, so called Resistive Processing Unit (RPU) devices, can provide significant power and speed benefits when trai…
Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices
Tayfun Gokmen, O. Murat Onen, Wilfried Haensch
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resisti…