We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods that have tackled this problem in a deterministic or non-parametric way, we propose to model future frames in a probabilistic manner. Our probabilistic model makes it possible for us to sample and synthesize many possible future frames from a single input image. To synthesize realistic movement of objects, we propose a novel network structure, namely a Cross Convolutional Network; this network encodes image and motion information as feature maps and convolutional kernels, respectively. In experiments, our model performs well on synthetic data, such as 2D shapes and animated game sprites, and on real-world video frames. We present analyses of the learned network representations, showing it is implicitly learning a compact encoding of object appearance and motion. We also demonstrate a few of its applications, including visual analogy-making and video extrapolation.

This paper presents a new ensemble learning method for classification problems called projection pursuit random forest (PPF). PPF uses the PPtree algorithm introduced in Lee et al. (2013). In PPF, trees are constructed by splitting on linear combinations of randomly chosen variables. Projection pursuit is used to choose a projection of the variables that best separates the classes. Utilizing linear combinations of variables to separate classes takes the correlation between variables into account which allows PPF to outperform a traditional random forest when separations between groups occurs in combinations of variables. The method presented here can be used in multi-class problems and is implemented into an R (R Core Team, 2018) package, PPforest, which is available on CRAN.

Fashion is a glamorous business. British fashion house Burberry recently sparked a massive outcry after burning £28 million of excess stock (as listed in its annual report), continuing a "brand protection" practice associated with other fashion labels like Louis Vuitton and Chanel. Far from protecting Burberry's brand, this backlash could not have come at a worse time for the label. The industry is already under intense scrutiny for years of unethical practices. In addition, fashion houses have to contend with changing tastes and shopping habits.

Maintaining assets such as compressors is an extremely complex endeavor: they are used in everything from small drilling rigs to deep-water platforms, the assets are located across the globe, and they generate terabytes of data daily. A failure for just one of these compressors costs millions of dollars of lost production per day. An important way to save time and money is to use machine learning to predict outages and issue maintenance work orders before the failure occurs. Ultimately, you need to build an end-to-end predictive data pipeline that can provide a real-time database to maintain asset parts and sensor mappings, support a continuous application that processes a massive amount of telemetry, and allows you to predict compressor failures against these datasets. Our approach to addressing these issues is by selecting a unified platform that offers these capabilities.

At this point, we have assembled our dataset and gained insights into the key characteristics of our data. Next, based on the metrics we gathered in Step 2, we should think about which classification model we should use. This means/ asking questions such as, "How do we present the text data to an algorithm that expects numeric input?" (this is called data preprocessing and vectorization), "What type of model should we use?", "What configuration parameters should we use for our model?", Thanks to decades of research, we have access to a large array of data preprocessing and model configuration options. However, the availability of a very large array of viable options to choose from greatly increases the complexity and the scope of the particular problem at hand.

Stochastic optimization is one of the effective approach to deal with the large-scale machine learning problems and the recent research has focused on reduction of variance, caused by the noisy approximations of the gradients, and momentum acceleration. In this paper, we have proposed simple variants of SAAG-I and II (Stochastic Average Adjusted Gradient) \cite{Chauhan2017Saag}, called SAAG-III and IV, respectively. Unlike SAAG-I, starting point is set to average of previous epoch in SAAG-III, and unlike SAAG-II, the snap point and starting point are set to average and last iterate of previous epoch, respectively. To determine the step size, we introduce Stochastic Backtracking-Armijo line Search (SBAS) which performs line search only on selected mini-batch of data points. Since backtracking line search is not suitable for large-scale problems and the constants used to find the step size, like Lipschitz constant, are not always available so SBAS could be very effective in such cases. We also extend SAAGs (I, II, III, IV), to solve non-smooth problems and design two update rules for smooth and non-smooth problems. Moreover, our theoretical results prove linear convergence of SAAG-IV for all the four combinations of smoothness and strong-convexity, in expectation. Finally, our experimental studies prove the efficacy of proposed methods against the state-of-art techniques, like, SVRG and VR-SGD.

Pieter Abbeel UC Berkeley In recent years, deep generative models have been shown to'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans - a plausible sequence of observations that transition a dynamical system from its current configuration to a desired goal state, which can later be used as a reference trajectory for control. We focus on systems with high-dimensional observations, such as images, and propose an approach that naturally combines representation learning and planning. Our framework learns a generative model of sequential observations, where the generative process is induced by a transition in a low-dimensional planning model, and an additional noise. By maximizing the mutual information between the generated observations and the transition in the planning model, we obtain a low-dimensional representation that best explains the causal nature of the data. We structure the planning model to be compatible with efficient planning algorithms, and we propose several such models based on either discrete or continuous states. Finally, to generate a visual plan, we project the current and goal observations onto their respective states in the planning model, plan a trajectory, and then use the generative model to transform the trajectory to a sequence of observations. We demonstrate our method on imagining plausible visual plans of rope manipulation.

It is a simple algorithm which can be used as a performance baseline. This algorithm methodology is used mostly for forecasting and finding out cause and effect relationship between data variables. Its purpose from a database is to read the data points which are separated into several classes and then predict the new sample point classification. It gives great results when used for textual data analysis. It is an unsupervised learning used in unlabelled data sources. However, it is mostly used in classification cases.

Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility to correct the model. There is therefore a need for transparency of machine learning models. The development of transparent classification models has received much attention, but there are few developments for achieving transparent Reinforcement Learning (RL) models. In this study we propose a method that enables a RL agent to explain its behavior in terms of the expected consequences of state transitions and outcomes. First, we define a translation of states and actions to a description that is easier to understand for human users. Second, we developed a procedure that enables the agent to obtain the consequences of a single action, as well as its entire policy. The method calculates contrasts between the consequences of a policy derived from a user query, and of the learned policy of the agent. Third, a format for generating explanations was constructed. A pilot survey study was conducted to explore preferences of users for different explanation properties. Results indicate that human users tend to favor explanations about policy rather than about single actions.

Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine pro- cessing. In this paper, we present AceKG, a new large-scale KG in academic domain. AceKG not only provides clean academic information, but also offers a large-scale benchmark dataset for researchers to conduct challenging data mining projects including link prediction, community detection and scholar classification. Specifically, AceKG describes 3.13 billion triples of academic facts based on a consistent ontology, including necessary properties of papers, authors, fields of study, venues and institutes, as well as the relations among them. To enrich the proposed knowledge graph, we also perform entity alignment with existing databases and rule-based inference. Based on AceKG, we conduct experiments of three typical academic data mining tasks and evaluate several state-of- the-art knowledge embedding and network representation learning approaches on the benchmark datasets built from AceKG. Finally, we discuss several promising research directions that benefit from AceKG.