The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents an efficient unipolar stochastic computing hardware for convolutional neural networks (CNNs). It includes stochastic ReLU and optimized max function, which are key components in a CNN. To avoid the range limitation problem of stochastic numbers and increase the signal-to-noise ratio, we perform weight normalization and upscaling. In addition, to reduce the overhead of binary-to-stochastic...
Stochastic computing has been adopted in various fields to improve the power efficiency of systems. Recent work showed that DNN based on stochastic computing can greatly reduce the power consumption. However, stochastic computing has a limitation of high latency overhead as it computes values only one bit per cycle. This paper proposes a new scheme to improve the latency of DNN implementation based...
As deep neural networks grow larger, they suffer from a huge number of weights, and thus reducing the overhead of handling those weights becomes one of key challenges nowadays. This paper presents a new approach to binarizing neural networks, where the weights are pruned and forced to take degenerate binary values. Experimental results show that the proposed approach achieves significant reductions...
Signed-digit adder, which eliminates carry propagation chain, can execute addition operation independent of the length of operands, in constant time. The confined carry propagation implies remarkable advantage in terms of error detection, localization, and correction. We developed a new low-cost technique, for fault-localization and error-correction, which utilizes the self-dual concept in binary...
This paper presents an efficient DNN design with stochastic computing. Observing that directly adopting stochastic computing to DNN has some challenges including random error fluctuation, range limitation, and overhead in accumulation, we address these problems by removing near-zero weights, applying weight-scaling, and integrating the activation function with the accumulator. The approach allows...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.