An automatic speech recognition (ASR) performance has greatly improved with the introduction of convolutional neural network (CNN) or long-short term memory (LSTM) for acoustic modeling. Recently, a convolutional LSTM (CLSTM) has been proposed to directly use convolution operation within the LSTM blocks and combine the advantages of both CNN and LSTM structures into a single architecture. Thi...

Conformant planning is the task of generating plans given uncertainty about the initial state and action effects, and without any sensing capabilities during plan execution. The plan should be successful regardless of which particular initial state we are in. This paper is motivated by the observation that (1) Conformant planning without conditional effects can be handled easily by any forward ...

A FEC group consists of N packets with k of them being data packets and N − k carrying redundant data. The coding efficiency of the FEC scheme is therefore k/N , and the redundancy is (N − k)/N . Data packets that are lost during transmission can be reconstructed if and only if a combination of at least k data and check packets of the N packet group are received correctly. When fewer than k pac...