Takayuki Yoshizumi

Regularized dynamic Boltzmann machine with Delay Pruning for unsupervised learning of temporal sequences

We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM). The recently introduced DyBM provides a particularly structured Boltzmann machine, as a generative model of a multi-dimensional time-series. This Boltzmann machine can have infinitely many layers of units but allows exact inference and learning based on its biologically motivated structure. DyBM uses the idea of conduction delays in the form of fixed length first-in first-out (FIFO) queues, with a neuron connected to another via this FIFO queue, and spikes from a pre-synaptic neuron travel along the queue to the post-synaptic neuron with a constant period of delay. Here, we present Delay Pruning as a mechanism to prune the lengths of the FIFO queues (making them zero) by setting some delay lengths to one with a fixed probability, and finally selecting the best performing model with fixed delays. The uniqueness of structure and a non-sampling based learning rule in DyBM, make the application of previously proposed regularization techniques like Dropout or DropConnect difficult, leading to poor generalization. First, we evaluate the performance of Delay Pruning to let DyBM learn a multidimensional temporal sequence generated by a Markov chain. Finally, we show the effectiveness of delay pruning in learning high dimensional sequences using the moving MNIST dataset, and compare it with Dropout and DropConnect methods.

A simulation-based algorithm for supply chain optimization

In a supply chain, there are wide variety of problems, such as transportation scheduling problems and warehouse location problems. These problems are independently defined as optimization problems, and algorithms have been proposed for each problem. It is difficult, however, to design an algorithm for optimizing a supply chain simultaneously because the problem is much more complex than the individual problems. We present a simulation-based optimization algorithm that optimizes a supply chain, exploiting both simulation and optimization techniques. This system leverages two existing algorithms, and will optimize a supply chain by executing simulations while changing the boundary conditions between the two algorithms. Experimental results show that a better solution to a supply chain can be found through a series of optimization simulations. A logistics consultant was satisfied with the solution. This system will be used in actual logistics consulting services.