Class incremental learning refers to a special multi-class classification task, in which the number of classes is not fixed but is increasing with the continual arrival of new data. Existing researches mainly focused on solving catastrophic forgetting problem in class incremental learning. To this end, however, these models still require the old classes cached in the auxiliary data structure or models, which is inefficient in space or time. In this paper, it is the first time to discuss the difficulty without support of old classes in class incremental learning, which is called as softmax suppression problem. To address these challenges, we develop a new model named Label Mapping with Response Consolidation (LMRC), which need not access the old classes anymore. We propose the Label Mapping algorithm combined with the multi-head neural network for mitigating the softmax suppression problem, and propose the Response Consolidation method to overcome the catastrophic forgetting problem. Experimental results on the benchmark datasets show that our proposed method achieves much better performance compared to the related methods in different scenarios.

We consider online learning in episodic loopfree We propose a novel algorithm for the adversarial MDP Markov decision processes (MDPs), where model where the transition function is unknown to the the loss function can change arbitrarily between learner and the losses change arbitrarily over time. Our episodes, and the transition function is not known algorithm, UC-O-REPS, uses two important ingredients, to the learner. We show Õ(L X A T) regret the first is Online Mirror Descent (OMD) (Shalev-Shwartz, bound, where T is the number of episodes, X 2012) and the second is UCRL-2 (Auer et al., 2008). A is the state space, A is the action space, and L major challenge in this work is to handle convex performance is the length of each episode. Our online algorithm criteria, which model different ways of aggregating is implemented using entropic regularization the losses of each episode. In order to handle convex performance methodology, which allows to extend the criteria, we use the methodology of OMD, which is original adversarial MDP model to handle convex widely used for online convex optimization, and we implement performance criteria (different ways to aggregate it in the adversarial MDP setting. In order to overcome the losses of a single episode), as well as the unknown dynamics (stochastic transition function) improve previous regret bounds.

Just five months after completing the acquisition of BlueData, Hewlett Packard Enterprise Tuesday unleased a new version of its artificial intelligence BlueData big data-as-a-service offering that runs on its high performance Apollo systems backed up by HPE Pointnext deployment services. With the new offering, HPE said BlueData software subscriptions can be ordered with HPE Apollo server and storage infrastructure in a variety of configurations. The new offering is available in the United States, United Kingdom/Ireland, Germany, France and Singapore. "The message is if you have a AI/data science expertise and you are in the five countries we are doing business in, we absolutely want you to be participating in the HPE channel with this technology stack," said Patrick Osborne, vice president and general manager of big data and secondary storage for Hewlett Packard Enterprise. In fact, the new integrated offering signals the start of a partner recruitment offensive aimed at driving high margin, recurring revenue big data opportunities for the channel.

SoftBank Group saw its operating income increase by 81% over the year to March 31, 2019, driven by its SoftBank Vision and Delta Funds more than tripling their operating income. Here's how it's related to artificial intelligence, how it works and why it matters. Overall, the SoftBank conglomerate took in ¥9.6 trillion in sales, an increase of 5%, from which it made ¥2.35 trillion in earnings before interest and taxes, up 81%, and ¥1.4 trillion of net income. Broken down, both of its telcos in the form of Sprint and SoftBank Corporation contributed around ¥3.7 trillion in sales, with Yahoo Japan making ¥947 billion in sales, and others making up the remaining ¥1.2 trillion. For operating income, the SoftBank Vision Fund hit ¥1.26 trillion, SoftBank made ¥725 billion, Sprint contributed ¥280 billion, and Yahoo Japan made ¥135 billion.

Twenty-five percent of customer service and support operations will integrate virtual customer assistant (VCA) or chatbot technology across engagement channels by 2020, up from less than two percent in 2017, according to Gartner, Inc. Speaking at the Gartner Customer Experience Summit in Tokyo today, Gene Alvarez, managing vice president at Gartner, said more than half of organizations have already invested in VCAs for customer service, as they realize the advantages of automated self-service, together with the ability to escalate to a human agent in complex situations. "As more customers engage on digital channels, VCAs are being implemented for handling customer requests on websites, mobile apps, consumer messaging apps and social networks," Mr. Alvarez said. "This is underpinned by improvements in natural-language processing, machine learning and intent-matching capabilities." Organizations report a reduction of up to 70 percent in call, chat and/or email inquiries after implementing a VCA, according to Gartner research. They also report increased customer satisfaction and a 33 percent saving per voice engagement.

Tree ensembles, such as random forests and AdaBoost, are ubiquitous machine learning models known for achieving strong predictive performance across a wide variety of domains. However, this strong performance comes at the cost of interpretability (i.e. users are unable to understand the relationships a trained random forest has learned and why it is making its predictions). In particular, it is challenging to understand how the contribution of a particular feature, or group of features, varies as their value changes. To address this, we introduce Disentangled Attribution Curves (DAC), a method to provide interpretations of tree ensemble methods in the form of (multivariate) feature importance curves. For a given variable, or group of variables, DAC plots the importance of a variable(s) as their value changes. We validate DAC on real data by showing that the curves can be used to increase the accuracy of logistic regression while maintaining interpretability, by including DAC as an additional feature. In simulation studies, DAC is shown to out-perform competing methods in the recovery of conditional expectations. Finally, through a case-study on the bike-sharing dataset, we demonstrate the use of DAC to uncover novel insights into a dataset.

Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex rewards, which require tedious hand-tuning. We automate the reward search with AutoRL, an evolutionary layer over standard RL that treats reward tuning as hyperparameter optimization and trains a population of RL agents to find a reward that maximizes the task objective. AutoRL, evaluated on four Mujoco continuous control tasks over two RL algorithms, shows improvements over baselines, with the the biggest uplift for more complex tasks. The video can be found at: \url{https://youtu.be/svdaOFfQyC8}.

For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN) that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE randomized GAN (VHE-GAN) encodes an image to decode its associated text, and feeds the variational posterior as the source of randomness into the GAN image generator. We plug three off-the-shelf modules, including a deep topic model, a ladder-structured image encoder, and StackGAN++, into VHE-GAN, which already achieves competitive performance. This further motivates the development of VHE-raster-scan-GAN that generates photo-realistic images in not only a multi-scale low-to-high-resolution manner, but also a hierarchical-semantic coarse-to-fine fashion. By capturing and relating hierarchical semantic and visual concepts with end-to-end training, VHE-raster-scan-GAN achieves state-of-the-art performance in a wide variety of image-text multi-modality learning and generation tasks. PyTorch code is provided.

Stock prediction is a topic undergoing intense study for many years. Finance experts and mathematicians have been working on a way to predict the future stock price so as to decide to buy the stock or sell it to make profit. Stock experts or economists, usually analyze on the previous stock values using technical indicators, sentiment analysis etc to predict the future stock price. In recent years, many researches have extensively used machine learning for predicting the stock behaviour. In this paper we propose data driven deep learning approach to predict the future stock value with the previous price with the feature extraction property of convolutional neural network and to use Neural Arithmetic Logic Units with it.

Factorization machines (FM) are a popular model class to learn pairwise interactions by a low-rank approximation. Different from existing FM-based approaches which use a fixed rank for all features, this paper proposes a Rank-Aware FM (RaFM) model which adopts pairwise interactions from embeddings with different ranks. The proposed model achieves a better performance on real-world datasets where different features have significantly varying frequencies of occurrences. Moreover, we prove that the RaFM model can be stored, evaluated, and trained as efficiently as one single FM, and under some reasonable conditions it can be even significantly more efficient than FM. RaFM improves the performance of FMs in both regression tasks and classification tasks while incurring less computational burden, therefore also has attractive potential in industrial applications.