We describe an algorithm for support vector machines (SVM) that can be parallelized efficiently and scales to very large problems with hundreds of thousands of training vectors. Instead of analyzingâ€¦ (More)

The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning andâ€¦ (More)

We present a massively parallel coprocessor for accelerating Convolutional Neural Networks (CNNs), a class of important machine learning algorithms. The coprocessor functional units, consisting ofâ€¦ (More)

We present a massively parallel FPGA-based coprocessor for Support Vector Machines (SVMs), a machine learning algorithm whose applications include recognition tasks such as learning scenes,â€¦ (More)

We present a new, massively parallel architecture for accelerating machine learning algorithms, based on arrays of vector processing elements (VPEs) with variable-resolution arithmetic. Groups ofâ€¦ (More)

We address the problem of how to reinforce learning in ultracomplex environments, with huge state-spaces, where one must learn to exploit a compact structure of the problem domain. The approach weâ€¦ (More)

We study the problem of how a computer program can learn, by interacting with an environment, to return an algorithm for solving a class of problems. We describe experiments with a learning system weâ€¦ (More)

We use the steam boiler control speci cation problem to illustrate how the evolving algebra approach to the speci cation and the veri cation of complex systems can be exploited for a reliable andâ€¦ (More)