著者
Koji KAMMA Toshikazu WADA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E104-D, no.1, pp.194-202, 2021-01-01
被引用文献数
2

This paper presents a pruning method, Reconstruction Error Aware Pruning (REAP), to reduce the redundancy of convolutional neural network models for accelerating their inference. In REAP, we have the following steps: 1) Prune the channels whose outputs are redundant and can be reconstructed from the outputs of other channels in each convolutional layer; 2) Update the weights of the remaining channels by least squares method so as to compensate the error caused by pruning. This is how we compress and accelerate the models that are initially large and slow with little degradation. The ability of REAP to maintain the model performances saves us lots of time and labors for retraining the pruned models. The challenge of REAP is the computational cost for selecting the channels to be pruned. For selecting the channels, we need to solve a huge number of least squares problems. We have developed an efficient algorithm based on biorthogonal system to obtain the solutions of those least squares problems. In the experiments, we show that REAP can conduct pruning with smaller sacrifice of the model performances than several existing methods including the previously state-of-the-art one.
著者
Justine Renauld Nicolas Thelen Odile Bartholomé Brigitte Malgrange Marc Thiry
出版者
Japan Society for Cell Biology
雑誌
Cell Structure and Function (ISSN:03867196)
巻号頁・発行日
pp.20057, (Released:2021-01-20)
被引用文献数
1

The development of hearing in mammals requires the formation and maturation of a highly organized and specialized epithelium known as the organ of Corti. This epithelium contains two types of cells, the sensory cells, which are the true receptors of auditory information, and the surrounding supporting cells, which are composed of a highly developed cytoskeleton essential to the architecture of the mature organ of Corti. The supporting cells are the only mammalian cells reported to contain the unusual 15-protofilament microtubules. In this paper, we show that 15-protofilament microtubules appear between the second and fourth day after birth in the pillar cells of the organ of Corti in mice. We also show that contrary to what has been described in the nematode worm Caenorhabiditis. Elegans, microtubule acetylation is not essential for the formation of 15-protofilament microtubules in mice but is required for fine-tuning of their diameter. Key words: Acetylation, cytoskeleton, microtubule, inner ear, supporting cells
著者
Akihiro MUSA Yoshiei SATO Ryusuke EGAWA Hiroyuki TAKIZAWA Koki OKABE Hiroaki KOBAYASHI
出版者
The Editorial Committee of the Interdisciplinary Information Sciences
雑誌
Interdisciplinary Information Sciences (ISSN:13409050)
巻号頁・発行日
vol.15, no.1, pp.51-66, 2009 (Released:2009-03-25)
参考文献数
21
被引用文献数
2 3

Thanks to the highly effective memory bandwidth of the vector systems, they can achieve the high computation efficiency for computation-intensive scientific applications. However, they have been encountering the memory wall problem and the effective memory bandwidth rate has decreased, resulting in the decrease in the bytes per flop rates of recent vector systems from 4 (SX-7 and SX-8) to 2 (SX-8R) and 2.5 (SX-9). The situation is getting worse as many functions units and/or cores will be brought into a single chip, because the pin bandwidth is limited and does not scale. To solve the problem, we propose an on-chip cache, called vector cache, to maintain the effective memory bandwidth rate of future vector supercomputers. The vector cache employs a bypass mechanism between the main memory and register files under software controls. We evaluate the performance of the vector cache on the NEC SX vector processor architecture with bytes per flop rates of 2 B/FLOP and 1 B/FLOP, to clarify the basic characteristics of the vector cache. For the evaluation, we use the NEC SX-7 simulator extended with the vector cache mechanism. Benchmark programs for performance evaluation are two DAXPY-like loops and five leading scientific applications. The results indicate that the vector cache boosts the computational efficiencies of the 2 B/FLOP and 1 B/FLOP systems up to the level of the 4 B/FLOP system. Especially, in the case where cache hit rates exceed 50%, the 2 B/FLOP system can achieve a performance comparable to the 4 B/FLOP system. The vector cache with the bypass mechanism can provide the data both from the main memory and the cache simultaneously. In addition, from the viewpoints of designing the cache, we investigate the impact of cache associativity on the cache hit rate, and the relationship between cache latency and the performance. The results also suggest that the associativity hardly affects the cache hit rate, and the effects of the cache latency depend on the vector loop length of applications. The cache shorter latency contributes to the performance improvement of the applications with shorter loop lengths, even in the case of the 4 B/FLOP system. In the case of longer loop lengths of 256 or more, the latency can effectively be hidden, and the performance is not sensitive to the cache latency. Finally, we discuss the effects of selective caching using the bypass mechanism and loop unrolling on the vector cache performance for the scientific applications. The selective caching is effective for efficient use of the limited cache capacity. The loop unrolling is also effective for the improvement of performance, resulting in a synergistic effect with caching. However, there are exceptional cases; the loop unrolling worsens the cache hit rate due to an increase in the working space to process the unrolled loops over the cache. In this case, an increase in the cache miss rate cancels the gain obtained by unrolling.