| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | Analisa |
| Volume / Nomor Edisi | : | IX-7, JULI (No. 7) |
| Nomor Halaman | : | 645-662 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | R.B. Suhartono |
| Nama Majalah/Jurnal | : | Analisa |
| Volume / Nomor Edisi | : | IX-7, JULI (No. 7) |
| Nomor Halaman | : | 620-644 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | Tanya Khovanova & Gregory Marton |
| Nama Majalah/Jurnal | : | The American Mathematical Monthly |
| Volume / Nomor Edisi | : | 132 (No. 8) |
| Nomor Halaman | : | 780-787 |
| Abstraksi Narasi | : | What follows is the story of a family of integer sequences, which started life as a Google interview puzzle back in the previous century when VHS video tapes were in use. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | IEEE Computational intelligence |
| Volume / Nomor Edisi | : | 10 (No. 2) |
| Nomor Halaman | : | 30-41 |
| Abstraksi Narasi | : | This paper presents a comprehensive methodology for general large-scale image-based classification tasks. It addresses the Big Data challenge in arbitrary image classifi- cation and more specifically, filtering of millions of websites with abstract target classes and high levels of label noise. Our approach uses local image features and their color descriptors to build image representations with the help of a modified k-NN algorithm. Image representations are refined into image and website class pre- dictions by a two-stage classifier method suitable for a very large-scale real dataset. A modification of an Extreme Learning Machine is found to be a suitable classifier technique. The methodology is robust to noise and can learn abstract target categories; website classification accuracy surpasses 97% for the most important categories considered in this study. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | Analisa |
| Volume / Nomor Edisi | : | IX-7, JULI (No. 7) |
| Nomor Halaman | : | 610-619 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | Soumya Bhattacharya |
| Nama Majalah/Jurnal | : | The American Mathematical Monthly |
| Volume / Nomor Edisi | : | 132 (No. 8) |
| Nomor Halaman | : | 779 |
| Abstraksi Narasi | : | Deskripsi abstrak ringkas tidak tersedia untuk artikel ini. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | Analisa |
| Volume / Nomor Edisi | : | IX-7, JULI (No. 7) |
| Nomor Halaman | : | 595-609 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | Azem Berivan Ad?belli & Haydar Goral |
| Nama Majalah/Jurnal | : | The American Mathematical Monthly |
| Volume / Nomor Edisi | : | 132 (No. 8) |
| Nomor Halaman | : | 766-778 |
| Abstraksi Narasi | : | We first prove the infinitude of the primes via a special case of Rado’s theorem whose proof is based on the infinite Ramsey theorem. In the proof, we use the colorings of the positive integers introduced by Levent Alpoge [Citation1] and Andrew Granville [Citation2]. Finally, using Rado’s theorem for integral domains, we will give another proof for the infinitude of nonassociated prime elements in any unique factorization domain R with a few units. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | Analisa |
| Volume / Nomor Edisi | : | IX-7, JULI (No. 7) |
| Nomor Halaman | : | 577-594 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | Guang-Bin Huang,Zuo Bai,Kasun, Liyanaarachchi Lekamalage Chamara,Chi Man Vong |
| Nama Majalah/Jurnal | : | IEEE Computational intelligence |
| Volume / Nomor Edisi | : | 10 (No. 2) |
| Nomor Halaman | : | 18-29 |
| Abstraksi Narasi | : | Extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks (SLFNs), provides efficient unified learning solutions for the applications of feature learning, clustering, regression and classification. Different from the common understanding and tenet that hidden neurons of neural networks need to be iteratively adjusted during training stage, ELM theories show that hidden neurons are important but need not be iteratively tuned. In fact, all the parameters of hidden nodes can be independent of training samples and randomly generated according to any continuous probability distribution. And the obtained ELM networks satisfy universal approximation and classification capability. The fully connected ELM architecture has been extensively studied. However, ELM with local connections has not attracted much research attention yet. This paper studies the general architecture of locally connected ELM, showing that: 1) ELM theories are naturally valid for local connections, thus introducing local receptive fields to the input layer; 2) each hidden node in ELM can be a combination of several hidden nodes (a subnetwork), which is also consistent with ELM theories. ELM theories may shed a light on the research of different local receptive fields including true biological receptive fields of which the exact shapes and formula may be unknown to human beings. As a specific example of such general architectures, random convolutional nodes and a pooling structure are implemented in this paper. Experimental results on the NORB dataset, a benchmark for object recognition, show that compared with conventional deep learning solutions, the proposed local receptive fields based ELM (ELM-LRF) reduces the error rate from 6.5% to 2.7% and increases the learning speed up to 200 times. |