Incremental Learning for Online Data Using QR Factorization on Convolutional Neural Networks.

Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the forgetting problem by learning new incoming data in an online manner. We develop a new incremental learning framework that can learn extra data or new classes with less catastrophic forgetting. We adopt the hippocampal memory process to the deep neural networks by defining the effective maximum of neural activation and its boundary to represent a feature distribution. In addition, we incorporate incremental QR factorization into the deep neural networks to learn new data with both existing labels and new labels with less forgetting. The QR factorization can provide the accurate subspace prior, and incremental QR factorization can reasonably express the collaboration between new data with both existing classes and new class with less forgetting. In our framework, a set of appropriate features (i.e., nodes) provides improved representation for each class. We apply our method to the convolutional neural network (CNN) for learning Cifar-100 and Cifar-10 datasets. The experimental results show that the proposed method efficiently alleviates the stability and plasticity dilemma in the deep neural networks by providing the performance stability of a trained network while effectively learning unseen data and additional new classes.

Surgical treatment of male breast cancer metastasis to thoracic spine: A case report.

PURPOSE: We present a rare clinical case of a metastatic spinal tumor in the 7th thoracic spine from male breast cancer (MBC). METHOD: A 62-year-old man was referred as an outpatient, complaining of continuous pain in the back and right flank that began 2 weeks earlier. The patient had no neurologic signs or symptoms but had a medical history of left breast modified radical mastectomy because of MBC. Computed tomography and magnetic resonance imaging showed metastasis in the T7 vertebra and no other metastasis on positron emission tomography/computed tomography or bone scan. Separation surgery was performed with posterior corpectomy of T7 (en bloc excision), followed by stabilization with an expandable titanium cage and pedicle screws. The pathological examination of the excised T7 vertebra confirmed metastatic carcinoma with neuroendocrine differentiation from the breast. Adjuvant chemo-radiotherapy was performed after surgery. RESULTS: The patient had no symptoms at the 21-month follow-up. Radiologic studies showed no evidence of recurrent or metastatic lesions. CONCLUSION: MBC is extremely rare, with fewer cases of spinal metastases. Among these, patients who undergo separation surgery are even rarer. This case shows that radical surgery can be an option for MBC with spine metastasis if indicated.

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance.