Fully-Parallel Area-Efficient Deep Neural Network Design Using Stochastic Computing
نویسندگان
چکیده
منابع مشابه
An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
With recent trend of wearable devices and Internet of Things (IoTs), it becomes attractive to develop hardware-based deep convolutional neural networks (DCNNs) for embedded applications, which require low power/energy consumptions and small hardware footprints. Recent works demonstrated that the Stochastic Computing (SC) technique can radically simplify the hardware implementation of arithmetic...
متن کاملtrajectory optimization of spherical parallel robots using artificial neural network
this article addresses an efficient and novel method for singularity-free path planning and obstacle avoidance of parallel manipulator based on neural networks. a modified 4-5-6-7 interpolating polynomial is used to plan a trajectory for a spherical parallel manipulator. the polynomial function which is smooth and continuous in displacement, velocity, acceleration and jerk is used to find a pat...
متن کاملFully parallel stochastic computation architecture
A space-efficient fully parallel stochastic computation architecture is described in this correspondence. It circumvents the main drawback of stochastic computation architectures that have been used up to now: the absence of a space-efficient technique of adding weighted input signals in parallel.
متن کاملSynchrony and asynchrony in a fully stochastic neural network.
We describe and analyze a model for a stochastic pulse-coupled neural network, in which the randomness in the model corresponds to synaptic failure and random external input. We show that the network can exhibit both synchronous and asynchronous behavior, and surprisingly, that there exists a range of parameters for which the network switches spontaneously between synchrony and asynchrony. We a...
متن کاملUsing Deep Neural Network Approximate Bayesian Network
We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint probability distribution of Bayesian Network by learning from a few observation and posterior probability distribution pairs with high accuracy. Compared with tradi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Circuits and Systems II: Express Briefs
سال: 2017
ISSN: 1549-7747,1558-3791
DOI: 10.1109/tcsii.2017.2746749