Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery.

Symbolic regression is a powerful technique to discover analytic equations that describe data, which can lead to explainable models and the ability to predict unseen data. In contrast, neural networks have achieved amazing levels of accuracy on image recognition and natural language processing tasks, but they are often seen as black-box models that are difficult to interpret and typically extrapolate poorly. In this article, we use a neural network-based architecture for symbolic regression called the equation learner (EQL) network and integrate it with other deep learning architectures such that the whole system can be trained end-to-end through backpropagation. To demonstrate the power of such systems, we study their performance on several substantially different tasks. First, we show that the neural network can perform symbolic regression and learn the form of several functions. Next, we present an MNIST arithmetic task where a convolutional network extracts the digits. Finally, we demonstrate the prediction of dynamical systems where an unknown parameter is extracted through an encoder. We find that the EQL-based architecture can extrapolate quite well outside of the training data set compared with a standard neural network-based architecture, paving the way for deep learning to be applied in scientific exploration and discovery.

Submental intubation: an alternative and cost-effective technique for complex maxillofacial surgeries.

INTRODUCTION: Management of airway is a significant issue especially in cases of complex maxillofacial trauma like panfacial fractures or concomitant nasoethmoidal injuries, where the nasotracheal intubation is contraindicated or possess a significant problem. In these cases the only other alternative is tracheostomy. Submental intubation is an alternative to tracheostomy and it can be easily performed with little or lesser post-operative complications. This method involves lesser expenses as it does away with longer post-operative stay in the hospital as required by tracheostomy patients. TECHNIQUE: The patient is orally intubated with a reinforced armoured tube with a detachable plastic gas connector. An incision is made in the submental area of the patient and a tunnel is prepared from this region to the floor of the mouth through which the proximal end of the tube is diverted. Thus the occlusion of the patient can be checked intraoperatively. After completion of the surgery the proximal end in reintroduced onto the oral cavity and the patient is extubated orally. DISCUSSION: Originally proposed by Altemir in 1986, this method cannot be used in all cases as it is not without limitations. In spite of these, submental intubation can be a useful alternative to tracheostomy, especially in regions where cost cutting is a major factor in health infrastructure. CONCLUSION: Maxillofacial surgeons addressing major facial trauma surgery may have this procedure in mind before opting for tracheostomy. It avoids a lot of complications associated with tracheostomy.