Data Partitioning google
Data partitioning in data mining is the division of the whole data available into two or three non overlapping sets: the training set , the validation set , and the test set. If the data set is very large, often only a portion of it is selected for the partitions. Partitioning is normally used when the model for the data at hand is being chosen from a broad set of models. The basic idea of data partitioning is to keep a subset of available data out of analysis, and to use it later for verification of the model. …

Deep Learning Accelerator Unit (DLAU) google
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses significant challenge to construct a high performance implementations of deep learning neural networks. In order to improve the performance as well to maintain the low power cost, in this paper we design DLAU, which is a scalable accelerator architecture for large-scale deep learning networks using FPGA as the hardware prototype. The DLAU accelerator employs three pipelined processing units to improve the throughput and utilizes tile techniques to explore locality for deep learning applications. Experimental results on the state-of-the-art Xilinx FPGA board demonstrate that the DLAU accelerator is able to achieve up to 36.1x speedup comparing to the Intel Core2 processors, with the power consumption at 234mW. …

Neural Decision Trees google
In this paper we propose a synergistic melting of neural networks and decision trees into a deep hashing neural network (HNN) having a modeling capability exponential with respect to its number of neurons. We first derive a soft decision tree named neural decision tree allowing the optimization of arbitrary decision function at each split node. We then rewrite this soft space partitioning as a new kind of neural network layer, namely the hashing layer (HL), which can be seen as a generalization of the known soft-max layer. This HL can easily replace the standard last layer of ANN in any known network topology and thus can be used after a convolutional or recurrent neural network for example. We present the modeling capacity of this deep hashing function on small datasets where one can reach at least equally good results as standard neural networks by diminishing the number of output neurons. Finally, we show that for the case where the number of output neurons is large, the neural network can mitigate the absence of linear decision boundaries by learning for each difficult class a collection of not necessarily connected sub-regions of the space leading to more flexible decision surfaces. Finally, the HNN can be seen as a deep locality sensitive hashing function which can be trained in a supervised or unsupervised setting as we will demonstrate for classification and regression problems. …

Advertisements