Deep learning approaches have shown remarkable performance in many areas of pattern recognition recently. In spite of their power in hierarchical feature extraction and classification, this type of neural network is computationally expensive and difficult to implement on hardware for portable devices. In an other vein of research on neural network architectures, spiking neural networks (SNNs) have been described as power-efficient models because of their sparse, spike-based communication framework. SNNs are brain-inspired such that they seek to mimic the accurate and efficient functionality of the brain. Recent studies try to take advantages of the both frameworks (deep learning and SNNs) to develop a deep architecture of SNNs to achieve high performance of recently proved deep networks while implementing bio-inspired, power-efficient platforms. Additionally, As the brain process different stimuli patterns through multi-layer SNNs that are communicating by spike trains via adaptive synapses, developing artificial deep SNNs can also be very helpful for understudying the computations done by biological neural circuits. Having both computational and experimental backgrounds, we are interested in including a comprehensive summary of recent advances in developing deep SNNs that may assist computer scientists interested in developing more advanced and efficient networks and help experimentalists to frame new hypotheses for neural information processing in the brain using a more realistic model.

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effective approach to reducing the communication volume. One key issue in gradient quantization is setting the number of bits for quantizing the gradients. Small number of bits can significantly reduce the communication overhead while hurts the gradient accuracies, and vise versa. An ideal quantization method would dynamically balance the communication overhead and model accuracy, through adjusting the number bits according to the knowledge learned from the immediate past training iterations. Existing methods, however, quantize the gradients either with fixed number of bits, or with predefined heuristic rules. In this paper we propose a novel adaptive quantization method within the framework of reinforcement learning. The method, referred to as MQGrad, formalizes the selection of quantization bits as actions in a Markov decision process (MDP) where the MDP states records the information collected from the past optimization iterations (e.g., the sequence of the loss function values). During the training iterations of a machine learning algorithm, MQGrad continuously updates the MDP state according to the changes of the loss function. Based on the information, MDP learns to select the optimal actions (number of bits) to quantize the gradients. Experimental results based on a benchmark dataset showed that MQGrad can accelerate the learning of a large scale deep neural network while keeping its prediction accuracies.

The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE) task. The proposed method, which is inspired by a statistical hypothesis test, consists of two phases: the first phase is to introduce the predictability of textual entailment labels as a null hypothesis which is extremely unacceptable if a target corpus has no hidden bias, and the second phase is to test the null hypothesis using a Naive Bayes model. The experimental result of the Stanford Natural Language Inference (SNLI) corpus does not reject the null hypothesis. Therefore, it indicates that the SNLI corpus has a hidden bias which allows prediction of textual entailment labels from hypothesis sentences even if no context information is given by a premise sentence. This paper also presents the performance impact of NN models for RTE caused by this hidden bias.

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from understanding its generation process. We present an unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialog models for interpretable response generation. Building upon variational autoencoders (VAEs), we present two novel models, DI-VAE and DI-VST that improve VAEs and can discover interpretable semantics via either auto encoding or context predicting. Our methods have been validated on real-world dialog datasets to discover semantic representations and enhance encoder-decoder models with interpretable generation.

As a data scientist who has been in the profession for several years now, I am often approached for career advice or guidance in course selection related to machine learning by students and career switchers on LinkedIn and Quora. Some questions revolve around educational paths and program selection, but many questions focus on what sort of algorithms or models are common in data science today. With a glut of algorithms from which to choose, it's hard to know where to start. Courses may include algorithms that aren't typically used in industry today, and courses may exclude very useful methods that aren't trending at the moment. Software-based programs may exclude important statistical concepts, and mathematically-based programs may skip over some of the key topics in algorithm design. I've put together a short guide for aspiring data scientists, particularly focused on statistical models and machine learning models (supervised and unsupervised); many of these topics are covered in textbooks, graduate-level statistics courses, data science bootcamps, and other training resources (some of which are included in the reference section of the article).

Flower pollination algorithm is a recent metaheuristic algorithm for solving nonlinear global optimization problems. The algorithm has also been extended to solve multiobjective optimization with promising results. In this work, we analyze this algorithm mathematically and prove its convergence properties by using Markov chain theory. By constructing the appropriate transition probability for a population of flower pollen and using the homogeneity property, it can be shown that the constructed stochastic sequences can converge to the optimal set. Under the two proper conditions for convergence, it is proved that the simplified flower pollination algorithm can indeed satisfy these convergence conditions and thus the global convergence of this algorithm can be guaranteed. Numerical experiments are used to demonstrate that the flower pollination algorithm can converge quickly in practice and can thus achieve global optimality efficiently.

URL: tthttp://www.cs.ru.nl/B.Jacobs This paper describes a new algorithm for exact Bayesian inference that is based on a recently proposed compositional semantics of Bayesian networks in terms of channels. The paper concentrates on the ideas behind this algorithm, involving a linearisation ('stretching') of the Bayesian network, followed by a combination of forward state transformation and backward predicate transformation, while evidence is accumulated along the way. The performance of a prototype implementation of the algorithm in Python is briefly compared to a standard implementation (pgmpy): first results show competitive performance.

The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data. This is due to its simplicity in the design of the procedure, as well as its robustness when applied to different type of problems. Since its publication in 2002, SMOTE has proven successful in a variety of applications from several different domains. SMOTE has also inspired several approaches to counter the issue of class imbalance, and has also significantly contributed to new supervised learning paradigms, including multilabel classification, incremental learning, semi-supervised learning, multi-instance learning, among others. It is standard benchmark for learning from imbalanced data. It is also featured in a number of different software packages -- from open source to commercial. In this paper, marking the fifteen year anniversary of SMOTE, we reflect on the SMOTE journey, discuss the current state of affairs with SMOTE, its applications, and also identify the next set of challenges to extend SMOTE for Big Data problems.

Machine learning applications often require hyperparameter tuning. The hyperparameters usually drive both the efficiency of the model training process and the resulting model quality. For hyperparameter tuning, machine learning algorithms are complex black-boxes. This creates a class of challenging optimization problems, whose objective functions tend to be nonsmooth, discontinuous, unpredictably varying in computational expense, and include continuous, categorical, and/or integer variables. Further, function evaluations can fail for a variety of reasons including numerical difficulties or hardware failures. Additionally, not all hyperparameter value combinations are compatible, which creates so called hidden constraints. Robust and efficient optimization algorithms are needed for hyperparameter tuning. In this paper we present an automated parallel derivative-free optimization framework called \textbf{Autotune}, which combines a number of specialized sampling and search methods that are very effective in tuning machine learning models despite these challenges. Autotune provides significantly improved models over using default hyperparameter settings with minimal user interaction on real-world applications. Given the inherent expense of training numerous candidate models, we demonstrate the effectiveness of Autotune's search methods and the efficient distributed and parallel paradigms for training and tuning models, and also discuss the resource trade-offs associated with the ability to both distribute the training process and parallelize the tuning process.

We show that the visible sector probability density function of the Riemann-Theta Boltzmann machine corresponds to a gaussian mixture model consisting of an infinite number of component multi-variate gaussians. The weights of the mixture are given by a discrete multi-variate gaussian over the hidden state space. This allows us to sample the visible sector density function in a straight-forward manner. Furthermore, we show that the visible sector probability density function possesses an affine transform property, similar to the multi-variate gaussian density.