Inverse Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks

We characterize and remedy a failure mode that may arise from multi-scale dynamics with scale imbalances during training of deep neural networks, such as Physics Informed Neural Networks (PINNs). PINNs are popular machine-learning templates that allow for seamless integration of physical equation models with data. Their training amounts to solving an optimization problem over a weighted sum of data-fidelity and equation-fidelity objectives. Conflicts between objectives can arise from scale imbalances, heteroscedasticity in the data, stiffness of the physical equation, or from catastrophic interference during sequential training. We explain the training pathology arising from this and propose a simple yet effective inverse Dirichlet weighting strategy to alleviate the issue. We compare with Sobolev training of neural networks, providing the baseline of analytically ε-optimal training. We demonstrate the effectiveness of inverse Dirichlet weighting in various applications, including a multi-scale model of active turbulence, where we show orders of magnitude improvement in accuracy and convergence over conventional PINN training. For inverse modeling using sequential training, we find that inverse Dirichlet weighting protects a PINN against catastrophic forgetting.

Moving Learning Machine towards Fast Real-Time Applications: A High-Speed FPGA-Based Implementation of the OS-ELM Training Algorithm

Currently, there are some emerging online learning applications handling data streams in real-time. The On-line Sequential Extreme Learning Machine (OS-ELM) has been successfully used in real-time condition prediction applications because of its good generalization performance at an extreme learning speed, but the number of trainings by a second (training frequency) achieved in these continuous learning applications has to be further reduced. This paper proposes a performance-optimized implementation of the OS-ELM training algorithm when it is applied to real-time applications. In this case, the natural way of feeding the training of the neural network is one-by-one, i.e., training the neural network for each new incoming training input vector. Applying this restriction, the computational needs are drastically reduced. An FPGA-based implementation of the tailored OS-ELM algorithm is used to analyze, in a parameterized way, the level of optimization achieved. We observed that the tailored algorithm drastically reduces the number of clock cycles consumed for the training execution up to approximately the 1%. This performance enables high-speed sequential training ratios, such as 14 KHz of sequential training frequency for a 40 hidden neurons SLFN, or 180 Hz of sequential training frequency for a 500 hidden neurons SLFN. In practice, the proposed implementation computes the training almost 100 times faster, or more, than other applications in the bibliography. Besides, clock cycles follows a quadratic complexity O ( N ˜ 2 ) , with N ˜ the number of hidden neurons, and are poorly influenced by the number of input neurons. However, it shows a pronounced sensitivity to data type precision even facing small-size problems, which force to use double floating-point precision data types to avoid finite precision arithmetic effects. In addition, it has been found that distributed memory is the limiting resource and, thus, it can be stated that current FPGA devices can support OS-ELM-based on-chip learning of up to 500 hidden neurons. Concluding, the proposed hardware implementation of the OS-ELM offers great possibilities for on-chip learning in portable systems and real-time applications where frequent and fast training is required.

Improving Would Healing Ability by Training: Experiences of China

In China, chronic wounds are an important issue. However, wound care knowledge and the skill of health care professionals varies among hospitals and cities. A training program in wound care in China was completed in 2015 and achieved great success. To facilitate expertise in wound healing in China, a sequential training project supported by the Wound Healing Union and the Chinese Medical Doctor Association was initiated. The aim of the training program was mainly to improve experience and skills in wound healing. Until December 2016, a total of 301 medical staffs, including 134 physicians and 167 nurses, have been trained. Most of the doctors (92 of 134) and nurses (142 of 167) were from Grade IIIA/B hospitals, and there were no doctors and nurses from community hospitals. Most participants were satisfied about the training program, and more nurses were satisfied (79%) than doctors (60%). All trainees have completed 4½ months of training and passed a final examination.

Dual Conditional GANs for Face Aging and Rejuvenation

Face aging and rejuvenation is to predict the face of a person at different ages. While tremendous progress have been made in this topic, there are two central problems remaining largely unsolved: 1) the majority of prior works requires sequential training data, which is very rare in real scenarios, and 2) how to simultaneously render aging face and preserve personality. To tackle these issues, in this paper, we develop a novel dual conditional GAN (DCGAN) mechanism, which enables face aging and rejuvenation to be trained from multiple sets of unlabeled face images with different ages. In our architecture, the primal conditional GAN transforms a face image to other ages based on the age condition, while the dual conditional GAN learns to invert the task. Hence a loss function that accounts for the reconstruction error of images can preserve the personal identity, while the discriminators on the generated images learn the transition patterns (e.g., the shape and texture changes between age groups) and guide the generation of age-specific photo-realistic faces. Experimental results on two publicly dataset demonstrate the appealing performance of the proposed framework by comparing with the state-of-the-art methods.

IMPLEMENTASI METODE SUPPORT VECTOR MACHINE UNTUK INDENTIFIKASI PENYAKIT DAUN TANAMAN KUBIS

Tanaman kubis merupakan salah satu sayuran yang banyak dikonsumsi masyarakat, dalam produksi bibit tanaman kubis sering mengalami hambatan karena serangan hama. Salah satu komponen dalam keberhasilan produksi kubis adalah masa perkembangan bibit, yang dikhawatirkan banyak mendapat serangan hama. Dalam penelitian ini pengolahan citra digital digunakan untuk mengidentifikasi hama/penyakit terhadap bibit tanaman kubis. Penelitian ini dimulai dengan pengumpulan citra daun tanaman kubis. Tahapan selanjutnya adalah pre-processing citra dengan menghilangkan background dari citra masukan kemudian dilakukan proses grayscale untuk mendapatkan nilai yang akan digunakan untuk proses selanjutnya. Hasil tersebut kemudian akan dihitung dengan menggunakan metode Support Vector Machine (SVM). Proses training dilakukan dengan Sequential Training yang kemudian dilakukan proses testing. Hasil dari klasifikasi dipengaruhi oleh proses segmentasi yang dilakukan serta input parameter yang digunakan saat proses training. Dari hasil pengujian menunjukkan rata-rata akurasi hasil klasifikasi mencapai 80.55%.