IDEAS 278,119 views SolidWorks Tutorial #181: Cola Bottle - Duration: 27:34. SolidWorks Tutorial 1,589,749 views Inside a Google data center - Duration: 5:28.

It should come as no surprise that demand for data scientists keeps going up. However, supply of data scientists has not kept pace, unfortunately (or fortunately, depending on your point of view). Thanks to the law of supply and demand, companies are being asked to pay annual salaries well into the six figures – and sometimes even seven or eight figures – to attract and retain top AI talent. In February, Element released an analysis of LinkedIn profiles that concluded there are only about 22,000 Ph.D.-carrying data science researchers and engineers worldwide who have the technical skills to deploy deep learning methodologies in a commercial setting. What's more, only about 3,000 of those data scientists are currently looking for a job – although it's common for companies to poach top data talent from competitors.

Last year, a novelist went on a road trip across the USA. The trip was an attempt to emulate Jack Kerouac--to go out on the road and find something essential to write about in the experience. There is, however, a key difference between this writer and anyone else talking your ear off in the bar. This writer is just a microphone, a GPS, and a camera hooked up to a laptop and a whole bunch of linear algebra. People who are optimistic that artificial intelligence and machine learning won't put us all out of a job say that human ingenuity and creativity will be difficult to imitate.

We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based intermediate representations for programs, and source languages. Based on these insights, we introduce a new graph-based intermediate representation (IR) which specifically aims to efficiently support fully-general AD for array programming. Unlike existing dataflow programming representations in ML frameworks, our IR naturally supports function calls, higher-order functions and recursion, making ML models easier to implement. The ability to represent closures allows us to perform AD using ST without a tape, making the resulting derivative (adjoint) program amenable to ahead-of-time optimization using tools from functional language compilers, and enabling higher-order derivatives. Lastly, we introduce a proof of concept compiler toolchain called Myia which uses a subset of Python as a front end.

Patient summarization is essential for clinicians to provide coordinated care and practice effective communication. Automated summarization has the potential to save time, standardize notes, aid clinical decision making, and reduce medical errors. Here we provide an upper bound on extractive summarization of discharge notes and develop an LSTM model to sequentially label topics of history of present illness notes. We achieve an F1 score of 0.876, which indicates that this model can be employed to create a dataset for evaluation of extractive summarization methods.

Recent progress on deep learning has made it possible to automatically transform the screenshot of Graphic User Interface (GUI) into code by using the encoder-decoder framework. While the commonly adopted image encoder (e.g., CNN network), might be capable of extracting image features to the desired level, interpreting these abstract image features into hundreds of tokens of code puts a particular challenge on the decoding power of the RNN-based code generator. Considering the code used for describing GUI is usually hierarchically structured, we propose a new attention-based hierarchical code generation model, which can describe GUI images in a finer level of details, while also being able to generate hierarchically structured code in consistency with the hierarchical layout of the graphic elements in the GUI. Our model follows the encoder-decoder framework, all the components of which can be trained jointly in an end-to-end manner. The experimental results show that our method outperforms other current state-of-the-art methods on both a publicly available GUI-code dataset as well as a dataset established by our own.

Brain cancer can be very fatal, but chances of survival increase through early detection and treatment. Doctors use Magnetic Resonance Imaging (MRI) to detect and locate tumors in the brain, and very carefully analyze scans to segment brain tumors. Manual segmentation is time consuming and tiring for doctors, and it can be difficult for them to notice extremely small abnormalities. Automated segmentations performed by computers offer quicker diagnoses, the ability to notice small details, and more accurate segmentations. Advances in deep learning and computer hardware have allowed for high-performing automated segmentation approaches. However, several problems persist in practice: increased training time, class imbalance, and low performance. In this paper, I propose applying V-Net, a volumetric, fully convolutional neural network, to segment brain tumors in MRI scans from the BraTS Challenges. With this approach, I achieve a whole tumor dice score of 0.89 and train the network in a short time while addressing class imbalance with the use of a dice loss layer. Then, I propose applying an existing technique to improve automated segmentation performance in practice.

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main enhancement subnetwork. Second, we scale the number of noise environments present at training time to 16,784 different environments. Experiment results show that both manipulations reduce word error rates of a pretrained speech recognition system and improve enhancement quality according to a number of performance measures. Specifically, our best model reduces the word error rate from 34.04% on noisy speech to 15.46% on the enhanced speech. Enhanced audio samples can be found in https://speechenhancement.page.link/samples.

However Deep neural networks recently have achieved impressive results for different tasks, they suffer from poor uncertainty prediction. Temperature Scaling (TS) is an efficient post-processing method for calibrating DNNs toward to have more accurate uncertainty prediction. TS relies on a single parameter T which softens the logit layer of a DNN and the optimal value of it is found by minimizing on Negative Log Likelihood (NLL) loss function. In this paper, we discuss about weakness of NLL loss function, especially for DNNs with high accuracy and propose a new loss function called Attended-NLL which can improve TS calibration ability significantly.

In this article, we show that solving the system of linear equations by manipulating the kernel and the range space is equivalent to solving the problem of least squares error approximation. This establishes the ground for a gradient-free learning search when the system can be expressed in the form of a linear matrix equation. When the nonlinear activation function is invertible, the learning problem of a fully-connected multilayer feedforward neural network can be easily adapted for this novel learning framework. By a series of kernel and range space manipulations, it turns out that such a network learning boils down to solving a set of cross-coupling equations. By having the weights randomly initialized, the equations can be decoupled and the network solution shows relatively good learning capability for real world data sets of small to moderate dimensions. Based on the structural information of the matrix equation, the network representation is found to be dependent on the number of data samples and the output dimension.