The field of natural language processing (NLP) makes it possible to understand patterns in large amounts of language data, from online reviews to audio recordings. But before a data scientist can really dig into an NLP problem, he or she must lay the groundwork that helps a model make sense of the different units of language it will encounter. Word embeddings are a set of feature engineering techniques widely used in predictive NLP modeling, particularly in deep learning applications. Word embeddings transform sparse vector representations of words into a dense, continuous vector space, enabling you to identify similarities between words and phrases -- on a large scale -- based on their context. In this piece, I'll explain the reasoning behind word embeddings and demostrate how to use these techniques to create clusters of similar words using data from 500,000 Amazon reviews of food. You can download the dataset to follow along.

Recent research implies that training and inference of deep neural networks (DNN) can be computed with low precision numerical representations of the training/test data, weights and gradients without a general loss in accuracy. The benefit of such compact representations is twofold: they allow a significant reduction of the communication bottleneck in distributed DNN training and faster neural network implementations on hardware accelerators like FPGAs. Several quantization methods have been proposed to map the original 32-bit floating point problem to low-bit representations. While most related publications validate the proposed approach on a single DNN topology, it appears to be evident, that the optimal choice of the quantization method and number of coding bits is topology dependent. To this end, there is no general theory available, which would allow users to derive the optimal quantization during the design of a DNN topology. In this paper, we present a quantization tool box for the TensorFlow framework. TensorQuant allows a transparent quantization simulation of existing DNN topologies during training and inference. TensorQuant supports generic quantization methods and allows experimental evaluation of the impact of the quantization on single layers as well as on the full topology. In a first series of experiments with TensorQuant, we show an analysis of fix-point quantizations of popular CNN topologies.

Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the factors are regularized by the sum of the product of squared Euclidean norms of the columns. Additionally, we inspect the case of a variable sized factorization and we prove that dropout achieves the global minimum of a convex approximation problem with (squared) nuclear norm regularization. As a result, we conclude that dropout can be used as a low-rank regularizer with data dependent singular-value thresholding.

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem. One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings. We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. Importantly, we highlight the limitations of existing approaches and point out future research directions in this existing new research area.

The resemblance between the methods used in studying quantum-many body physics and in machine learning has drawn considerable attention. In particular, tensor networks (TNs) and deep learning architectures bear striking similarities to the extent that TNs can be used for machine learning. Previous results used one-dimensional TNs in image recognition, showing limited scalability and a high bond dimension. In this work, we train two-dimensional hierarchical TNs to solve image recognition problems, using a training algorithm derived from the multipartite entanglement renormalization ansatz (MERA). This approach overcomes scalability issues and implies novel mathematical connections among quantum many-body physics, quantum information theory, and machine learning. While keeping the TN unitary in the training phase, TN states can be defined, which optimally encodes each class of the images into a quantum many-body state. We study the quantum features of the TN states, including quantum entanglement and fidelity. We suggest these quantities could be novel properties that characterize the image classes, as well as the machine learning tasks. Our work could be further applied to identifying possible quantum properties of certain artificial intelligence methods.

The introduction of data analytics into medicine has changed the nature of patient treatment. In this, patients are asked to disclose personal information such as genetic markers, lifestyle habits, and clinical history. This data is then used by statistical models to predict personalized treatments. However, due to privacy concerns, patients often desire to withhold sensitive information. This self-censorship can impede proper diagnosis and treatment, which may lead to serious health complications and even death over time. In this paper, we present privacy distillation, a mechanism which allows patients to control the type and amount of information they wish to disclose to the healthcare providers for use in statistical models. Meanwhile, it retains the accuracy of models that have access to all patient data under a sufficient but not full set of privacy-relevant information. We validate privacy distillation using a corpus of patients prescribed to warfarin for a personalized dosage. We use a deep neural network to implement privacy distillation for training and making dose predictions. We find that privacy distillation with sufficient privacy-relevant information i) retains accuracy almost as good as having all patient data (only 3\% worse), and ii) is effective at preventing errors that introduce health-related risks (only 3.9\% worse under- or over-prescriptions).

Sebastian Raschka, author of the bestselling book, Python Machine Learning, has many years of experience with coding in Python, and he has given several seminars on the practical applications of data science, machine learning, and deep learning, including a machine learning tutorial at SciPy - the leading conference for scientific computing in Python. While Sebastian's academic research projects are mainly centered around problem-solving in computational biology, he loves to write and talk about data science, machine learning, and Python in general, and he is motivated to help people develop data-driven solutions without necessarily requiring a machine learning background. His work and contributions have recently been recognized by the departmental outstanding graduate student award 2016-2017, as well as the ACM Computing Reviews' Best of 2016 award. In his free time, Sebastian loves to contribute to open source projects, and the methods that he has implemented are now successfully used in machine learning competitions, such as Kaggle. Vahid Mirjalili obtained his PhD in mechanical engineering working on novel methods for large-scale, computational simulations of molecular structures.

The power of Algorithms to calculate, contemplate and anticipate the needs of patients is improving rapidly and still has no sign of slowing down. Everything from patient diagnosis to therapy selection will soon be moving at exponential rates. Does that mean the end of doctors? To better understand technology's ever-growing role in healthcare, we first have to better examine the potential of tools and timelines that we are working with. A recent study done at Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School, showed that AI isn't about Humans versus Machines. They trained a Deep Learning Algorithm for identifying Metastatic Breast Cancer, interpreting pathology images.

Microsoft and Amazon, which surprised the tech world with a partnership between their Cortana and Alexa virtual assistants, are back at it again. Amazon Web Services and Microsoft's AI and Research Group this morning announced a new open-source deep learning interface called Gluon, jointly developed by the companies to let developers "prototype, build, train and deploy sophisticated machine learning models for the cloud, devices at the edge and mobile apps," according to an announcement just released by the companies. Deep learning involves training a computer to recognize patterns or unlock insights based on a set of rules for parsing a massive pool of data. As you might expect, this is an extremely complicated and time-consuming process that requires a fair amount of skill. Cloud companies offer ways to speed up the process, but a fair amount of skill is required to get meaningful results.