According to the MIT engineers, their new machine learning technique enables them to see even the tiniest imperfections in transparent objects. In a paper published by the MIT engineers in the journal Physical Review Letters, the team reported how they used a deep neural network to reconstruct transparent objects from images of the same objects taken in pitch-black conditions. The MIT researchers reportedly trained the neural network to associate specific inputs with corresponding outputs. In the team's experiment, the inputs were the dark, grainy images of the transparent objects. They then used outputs of the objects themselves.

GitHub is one of the most popular sources and this year GitHub featured a lot of open source projects. It also saw a record number of new users coming to GitHub and hosted over 100 million repositories. While there have been a lot of projects, there were a few that grabbed more popularity than the others. In this article, we list the top 10 open source projects by unique contributors that were used the most, which is largely decided by the number of stars received by the projects. BERT or Bidirectional Encoder Representations from Transformers is an all-new method of pre-training language representations. It is the first unsupervised, deeply bidirectional system for pre-training natural language processing (NLP) and obtains new state-of-the-art results on eleven NLP tasks.

Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input vector sequence, (ii) one adaptive weight matrix multiplied by the previous memory/state vector, and (iii) one adaptive bias vector. In effect, they augment the simple Recurrent Neural Networks (sRNNs) structure with the addition of a "memory cell" and the incorporation of at most 3 gating signals. The standard LSTM structure and components encompass redundancy and overly increased parameterization. In this paper, we systemically introduce variants of the LSTM RNNs, referred to as SLIM LSTMs. These variants express aggressively reduced parameterizations to achieve computational saving and/or speedup in (training) performance---while necessarily retaining (validation accuracy) performance comparable to the standard LSTM RNN.

Zeroth-order optimization or derivative-free optimization is an important research topic in machine learning. In recent, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract Hessian information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel \emph{Hessian-aware zeroth-order algorithm} called \texttt{ZO-HessAware}. Our theoretical result shows that \texttt{ZO-HessAware} has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods of such. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity.

Access to a large variety of data across a massive population has made it possible to predict customer purchase patterns and responses to marketing campaigns. In particular, accurate demand forecasts for popular products with frequent repeat purchases are essential since these products are one of the main drivers of profits. However, buyer purchase patterns are extremely diverse and sparse on a per-product level due to population heterogeneity as well as dependence in purchase patterns across product categories. Traditional methods in survival analysis have proven effective in dealing with censored data by assuming parametric distributions on inter-arrival times. Distributional parameters are then fitted, typically in a regression framework. On the other hand, neural-network based models take a non-parametric approach to learn relations from a larger functional class. However, the lack of distributional assumptions make it difficult to model partially observed data. In this paper, we model directly the inter-arrival times as well as the partially observed information at each time step in a survival-based approach using Recurrent Neural Networks (RNN) to model purchase times jointly over several products. Instead of predicting a point estimate for inter-arrival times, the RNN outputs parameters that define a distributional estimate. The loss function is the negative log-likelihood of these parameters given partially observed data. This approach allows one to leverage both fully observed data as well as partial information. By externalizing the censoring problem through a log-likelihood loss function, we show that substantial improvements over state-of-the-art machine learning methods can be achieved. We present experimental results based on two open datasets as well as a study on a real dataset from a large retailer.

A capsule is a group of neurons, whose activity vector represents the instantiation parameters of a specific type of entity. In this paper, we explore the capsule networks used for relation extraction in a multi-instance multi-label learning framework and propose a novel neural approach based on capsule networks with attention mechanisms. We evaluate our method with different benchmarks, and it is demonstrated that our method improves the precision of the predicted relations. Particularly, we show that capsule networks improve multiple entity pairs relation extraction.

The field of machine learning has gone through enormous changes in the last decades. Admittedly, there are some methods that have been around for a long time and are still a staple of the field. For example, the concept of least squares was already proposed in the early 19th century by Legendre and Gauss. Other approaches such as neural networks, whose most basic form was introduced in 1958, were substantially advanced in the last decades, while other methods such as support vector machines (SVMs) are even more recent. Due to the large number of available approaches for supervised learning, the following question is often posed: What is the best model?

There is a huge growth in machine learning development in the past few months. It is due to the availability of various open source tools that can create applications easily.- While the Python programming language feeds most machine learning frameworks, JavaScript has not lagged behind. This is the reason why JavaScript developers are using a number of frameworks for training and implementing machine learning models in the browser. In this blog, we will discuss various top machine learning JavaScript frameworks that you must consider for your online business growth in 2019.

At some fundamental level, no one understands machine learning. It isn't a matter of things being too complicated. Almost everything we do is fundamentally very simple. Unfortunately, an innate human handicap interferes with us understanding these simple things. Humans evolved to reason fluidly about two and three dimensions. With some effort, we may think in four dimensions. Machine learning often demands we work with thousands of dimensions – or tens of thousands, or millions! Even very simple things become hard to understand when you do them in very high numbers of dimensions. Reasoning directly about these high dimensional spaces is just short of hopeless.

I certainly can't speak about all books on the market. However, since the first edition was released, I engaged in countless discussions with my readers, to help them with particular questions and to get their opinion on the parts they found unclear or topics they wish I had covered. The connection between theory and praxis in particular was what readers found most helpful and somewhat lacking from other introductory texts (which, I heard, were either too theoretical or too practical). This constructive feedback has been invaluable for the second edition, helping me to focus on those parts that were still left unclear. In a nutshell, the second edition of Python Machine Learning provides a healthy mix of theory and practical examples that most people found so helpful in the first edition, and the second edition adds on top of it with many refinements and additional topics based on the large corpus of invaluable reader feedback.