As one of Bayesian analysis tools, Hidden Markov Model (HMM) has been used to in extensive applications. Most HMMs are solved by Baum-Welch algorithm (BWHMM) to predict the model parameters, which is difficult to find global optimal solutions. This paper proposes an optimized Hidden Markov Model with Particle Swarm Optimization (PSO) algorithm and so is called PSOHMM. In order to overcome the statistical constraints in HMM, the paper develops re-normalization and re-mapping mechanisms to ensure the constraints in HMM. The experiments have shown that PSOHMM can search better solution than BWHMM, and has faster convergence speed.

-- Poultry farms are an important contributor to the human food chain. Worldwide, humankind keeps an enormous number of domesticated birds (e.g. However, around the world, there have been growing concerns about the quality of life for the livestock in poultry farms; and increasingly vocal demands for improved standards of animal welfare. Recent advances in sensing technologies and machine learning allow the possibility of automatically assessing the health of some individual birds, and employing the lessons learned to improve the welfare for all birds. This task superficially appears to be easy, given the dramatic progress in recent years in classifying human behaviors, and given that human behaviors are presumably more complex. However, as we shall demonstrate, classifying chicken behaviors poses several unique challenges, chief among which is creating a generalizable "dictionary" of behaviors from sparse and noisy data. In this work we introduce a novel time series dictionary learning algorithm that can robustly learn from weakly labeled data sources. Poultry farms are a major source of high-protein and low-fat food. Given the ever-increasing population of the world, the demand for such food sources has been steadily growing. According to Food and Agriculture Organization of the United Nations (FAO), poultry meat consumption around the world has climbed from 11 kg/person in 2000 to 14.1 kg/person in 2011 [2]; and it is predicted to continue for the foreseeable future [3].

In our work, we propose to represent HTM as a set of flat models, or layers, and a set of topical hierarchies, or edges. We suggest several quality measures for edges of hierarchical models, resembling those proposed for flat models. We conduct an assessment experimentation and show strong correlation between the proposed measures and human judgement on topical edge quality. We also introduce heterogeneous algorithm to build hierarchical topic models for heterogeneous data sources. We show how making certain adjustments to learning process helps to retain original structure of customized models while allowing for slight coherent modifications for new documents. We evaluate this approach using the proposed measures and show that the proposed heterogeneous algorithm significantly outperforms the baseline concat approach. Finally, we implement our own ESE called Rysearch, which demonstrates the potential of ARTM approach for visualizing large heterogeneous document collections.

Based on 46 in-depth interviews with scientists, engineers, and CEOs, this document presents a list of concrete machine research problems, progress on which would directly benefit tech ventures in East Africa. The goal of this work is to give machine learning researchers a fuller picture of where and how their efforts as scientists can be useful. The goal is thus not to highlight research problems that are unique to East Africa -- indeed many of the problems listed below are of general interest in machine learning. The problems on the list are united solely by the fact that technology practitioners and organizations in East Africa reported a pressing need for their solution. The author is aware that listing machine learning problems without also providing data for them is not a recipe for getting those problems solved. If the reader is interested in any of the problems below, please get in touch.

These words of wisdom found their way to that part of my brain responsible with long-term memory after watching RIO 2. There was something about that toucan that made this phrase stick. Couple this philosophy with the idea that interviewing and recruiting talent is just like dating and the fact that full time employees spend more time at work than with their spouses at home, and I think you'll agree that working relationships between employees and employers are a lot like marriage. It's not uncommon for companies to take employees for granted and think that just because they are on payroll they will always give 110% or that they will be loyal forever and ever. When all companies want is to take, take, take and think that employees should only give, give, give, their relationship will eventually suffer and their employee turnover rate will get big, big, big. But when both parties treat each other right, and play with all cards on the table, things change.

Thanks to António Alegria, Head of AI at OutSystems for taking me through how OutSystems is using AI to improve the quality and speed of software development. António also heads up OutSystems' AI Center of Excellence -- Project Turing. António began his presentation explaining that tools were key to humanity's progress and that software became the ultimate tool to drive great achievements. The tools to create software have evolved; however, there is still room to grow -- program complexity is growing, we still have to manually update our games and TVs. The best way to address complexity is to take a complex problem and to break into smaller components.

Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Network models under non-stationary environments. The result shows that our proposed model can preserve the key information and adapts better to the changes. The accuracy of proposed model decreases by 0.4% in our experiments, while the accuracy of conventional model decreases by 90% in the drifts environment.

Adaptive moment methods have been remarkably successful in deep learning optimization, particularly in the presence of noisy and/or sparse gradients. We further the advantages of adaptive moment techniques by proposing a family of double adaptive stochastic gradient methods~\textsc{DASGrad}. They leverage the complementary ideas of the adaptive moment algorithms widely used by deep learning community, and recent advances in adaptive probabilistic algorithms.We analyze the theoretical convergence improvements of our approach in a stochastic convex optimization setting, and provide empirical validation of our findings with convex and non convex objectives. We observe that the benefits of~\textsc{DASGrad} increase with the model complexity and variability of the gradients, and we explore the resulting utility in extensions of distribution-matching multitask learning.

Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning. In this work, we propose a novel unsupervised representation learning framework called neighbor-encoder, in which domain knowledge can be easily incorporated into the learning process without modifying the general encoder-decoder architecture of the classic autoencoder.In contrast to autoencoder, which reconstructs the input data itself, neighbor-encoder reconstructs the input data's neighbors. As the proposed representation learning problem is essentially a neighbor reconstruction problem, domain knowledge can be easily incorporated in the form of an appropriate definition of similarity between objects. Based on that observation, our framework can leverage any off-the-shelf similarity search algorithms or side information to find the neighbor of an input object. Applications of other algorithms (e.g., association rule mining) in our framework are also possible, given that the appropriate definition of neighbor can vary in different contexts. We have demonstrated the effectiveness of our framework in many diverse domains, including images, text, and time series, and for various data mining tasks including classification, clustering, and visualization. Experimental results show that neighbor-encoder not only outperforms autoencoder in most of the scenarios we consider, but also achieves the state-of-the-art performance on text document clustering.

Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et al., 1999). However, only recently in (Bacon et al., 2017) was a policy gradient theorem derived for online learning of general purpose options in an end to end fashion. In this work, we extend previous work on this topic that only focuses on learning a two-level hierarchy including options and primitive actions to enable learning simultaneously at multiple resolutions in time. We achieve this by considering an arbitrarily deep hierarchy of options where high level temporally extended options are composed of lower level options with finer resolutions in time. We extend results from (Bacon et al., 2017) and derive policy gradient theorems for a deep hierarchy of options. Our proposed hierarchical option-critic architecture is capable of learning internal policies, termination conditions, and hierarchical compositions over options without the need for any intrinsic rewards or subgoals. Our empirical results in both discrete and continuous environments demonstrate the efficiency of our framework.