Deferred Dropout: An Algorithm-Hardware Co-Design DNN Training Method Provisioning Consistent High Activation Sparsity

Author(s):  
Kangkyu Park ◽  
Yunki Han ◽  
Lee-Sup Kim
2011 ◽  
Author(s):  
Ira Schurig ◽  
Steven Jarrett ◽  
Winfred Arthur ◽  
Ryan M. Glaze ◽  
Margaret Schurig

2020 ◽  
Vol 19 (1) ◽  
pp. 13
Author(s):  
Leury Max Da Silva Chaves ◽  
Gabriel Vinicius Santos ◽  
Cauê La Scala Teixeira ◽  
Marzo Edir Da Silva-Grigoletto

 Bodyweight exercises (also popularly known as calisthenics) is a classic training method and its practice has been widespread since the 19th century, but little evidenced in the scientific literature over the years. This type of training aims to promote multi-system adaptations using body weight as an overload with no or few implements [1–3]. This characteristic makes exercise with body weight easy to apply, in addition to having an excellent cost-benefit ratio when compared to other training possibilities that require machines or materials [4,5].


2019 ◽  
Vol 8 (2) ◽  
pp. 435
Author(s):  
Lystia Nurhaliza Hasibuan ◽  
R. Triyanto ◽  
Raden Burhan ◽  
Mangatas Mangatas

AbstrakPenelitian ini dilaksanakan di SMK Negeri 9 Medan, Jenis penelitian yaitu Penelitian Tindakan Kelas. Subjek penelitian ini adalah siswa kelas X DKV 1 yang berjumlah 36 orang siswa terdiri dari 20 laki-laki dan 16 perempuan, Penelitian ini bertujuan untuk meningkatkan hasil belajar sketsa, melalui motode demonstrasi dan latihan. Berdasarkan hasil observasi awal yang di temukan oleh peneliti, masih rendahnya hasil belajar sketsa siswa. Peneliti melakukan pre test untuk mengetahui kondisi awal sebelum dilaksanakannya tindakan persiklus. Hasil pre test menunjukkan masih rendahnya ketuntasan belajar siswa, dari 36 orang siswa hanya 7 orang siswa (19,4%) yang tuntas dalam pembelajaran sketsa. Penelitian ini menggunakan motode pembelajaran demonstrasi dan latihan. Pada siklus I diperoleh 24 orang siswa (66,7%) yang tuntas dan 12 orang siswa (33,3%) yang tidak tuntas. Dengan begitu, peneliti melanjutkan ke siklus II dengan perolehan 35 orang siswa (97,2%) yang tuntas dan 1 orang siswa (2,8%) tidak tuntas dalam pembelajaran sketsa. Terdapat peningkatan dari siklus I ke siklus II sebesar 30,5%, maka peneliti tidak melanjutkan ke siklus berikutnya. Dengan demikian dapat disimpulkan bahwa penggunaan motode pembelajaran demonstrasi dan latihan dapat meningkatkan kemampuan belajar sketsa pada siswa kelas X DKV 1 di SMK Negeri 9 Medan Tahun Pembelajaran 2019/2020.Kata Kunci: hasil belajar, sketsa, demonstrasi, latihan.AbstractThis research was conducted at SMK Negeri 9 Medan. The research employs a classroom action research method. The research subject was the ten grade students of DKV 1 with a total of 36 students consist of 20 men and 16 women. This research aims to improve skectch learning outcomes through demonstration and training method. Based on the results of preliminary observations found by researcher, the researcher found the low student sketch learning outcomes. The researcher used a pre-test to determine the initial conditions before the pre-cycle action was carried out. The result of pre-test showed that students' learning completeness was still low. From 36 students only 7 students (19,4%) who complete in sketching learning. This research was taught by using demonstration and training learning method. In cycle I, there were 24 students (66,7%) was complete and 12 students (33,3%) was incomplete. Therefore, the researcher proceed to cycle II with the acquisition of 35 students (97,2%) was complete and 1 students (2,8%) was incomplete in sketch learning. There was increase from cycle I to cycle II of 30,5%, the researcher does not proceed to the next cycle. Thus, it can be concluded that the use of demonstration and training method can improve the ability in sketch learning of the ten grade students DKV I at SMK Negeri 9 Medan in the academic year 2019/2020. Keywords: learning outcomes, sketch, demonstration, training.


2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).


2014 ◽  
Author(s):  
Kenton R. Kaufman ◽  
Mark Grabiner ◽  
Marilynn Wyatt ◽  
Pinata Sessoms
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document