In this paper, the echo state network (ESN) memory capacity, which represents the amount of input data an ESN can store, is analyzed for a new type of deep ESNs. In particular, two deep ESN architectures are studied. First, a parallel deep ESN is proposed in which multiple reservoirs are connected in parallel allowing them to average outputs of multiple ESNs, thus decreasing the prediction error. Then, a series architecture ESN is proposed in which ESN reservoirs are placed in cascade that the output of each ESN is the input of the next ESN in the series. This series ESN architecture can capture more features between the input sequence and the output sequence thus improving the overall prediction accuracy. Fundamental analysis shows that the memory capacity of parallel ESNs is equivalent to that of a traditional shallow ESN, while the memory capacity of series ESNs is smaller than that of a traditional shallow ESN.In terms of normalized root mean square error, simulation results show that the parallel deep ESN achieves 38.5% reduction compared to the traditional shallow ESN while the series deep ESN achieves 16.8% reduction.

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Depression and anxiety are critical public health issues affecting millions of people around the world. To identify individuals who are vulnerable to depression and anxiety, predictive models have been built that typically utilize data from one source. Unlike these traditional models, in this study, we leverage a rich heterogeneous data set from the University of Notre Dame's NetHealth study that collected individuals' (student participants') social interaction data via smartphones, health-related behavioral data via wearables (Fitbit), and trait data from surveys. To integrate the different types of information, we model the NetHealth data as a heterogeneous information network (HIN). Then, we redefine the problem of predicting individuals' mental health conditions (depression or anxiety) in a novel manner, as applying to our HIN a popular paradigm of a recommender system (RS), which is typically used to predict the preference that a person would give to an item (e.g., a movie or book). In our case, the items are the individuals' different mental health states. We evaluate three state-of-the-art RS approaches. Also, we model the prediction of individuals' mental health as another problem type -- that of node classification (NC) in our HIN, evaluating in the process four node features under logistic regression as a proof-of-concept classifier. We find that our RS and NC network methods produce more accurate predictions than a logistic regression model using the same NetHealth data in the traditional non-network fashion as well as a random-approach. Also, we find that RS outperforms NC. This is the first study to integrate smartphone, wearable sensor, and survey data in an HIN manner and use RS or NC on the HIN to predict individuals' mental health conditions.

This work is done as part of a master's thesis project. The increase in the volume of data has given rise to various issues related to the collection, storage, analysis and exploitation of these data in order to create an added value. In this master, we are interested in the search of frequent closed patterns in the transaction bases. One way to process data is to partition the search space into subcontexts, and then explore the subcontexts simultaneously. In this context, we have proposed a new approach for extracting frequent closed itemsets. The main idea is to update frequent closed patterns with their minimal generators by applying a strategy of partitioning of the initial extraction context. Our new approach called UFCIGs-DAC was designed and implemented to perform a search in the test bases. The main originality of this approach is the simultaneous exploration of the research space by the update of the frequent closed patterns and the minimal generators. Moreover, our approach can be adapted to any algorithm of extraction of the frequent closed patterns with their minimal generators.

Image-processing algorithms to smartly identify, caption and moderate your pictures. Convert spoken audio into text, use voice for verification, or add speaker recognition to your app. Allow your apps to process natural language with pre-built scripts, evaluate sentiment and learn how to recognize what users want. Map complex information and data in order to solve tasks such as intelligent recommendations and semantic search. Add Google or Bing Search APIs to your apps and harness the ability to comb billions of webpages, images, videos, news and much more.

The spread of tuberculosis (TB) has diminished in the developed world, but it is still prevalent in the developing parts of the world such as in Asia and Africa. The rise of HIV in the 1980's also saw an increase in TB infections due to the weakened immune systems of patients with HIV. Currently about 1.6 million people die from TB each year, and 10 million people develop active TB infections, which is also contagious. Tuberculosis is caused by Mycobacterium tuberculosis bacteria and it generally affects the lungs. Individuals can harbor the TB bacteria but show no symptoms.

What can we do about algorithmic bias? If you're a software developer or data scientist, IBM Research has an open source toolkit that helps you check bias in your data models. But it's not just technologists who can do something about algorithmic bias. You can start reclaiming digital space by exploring your choice in technology services. For example, by using search engines like DuckDuckGo, because unlike the voracious data vampire that is Google, it doesn't store your personal information to then use for targeted ads. You can also petition and lobby your government to adopt a governance framework for algorithmic accountability and transparency policy where "Algorithmic literacy" is introduced into curricular, and standardised notifications (to communicate type and degree of algorithmic processing in decisions) are made a requirement. Ultimately, we need to ask more of ourselves and tech companies. It's not enough to just employ critical thinking – we also need to employ civic thinking in how we build and use these technologies. This article first appeared in The Daily Maverick.

Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks by making a positivity assumption of the Gram-matrix of the neural tangent kernel. However, the performance of gradient descent on classification problems has not been well studied, and further investigation of the problem structure is possible. In this work, we present a partially stronger but reasonable assumption for binary classification problems compared to the positivity assumption of the Gram-matrix, where a data distribution can be perfectly classifiable by a tangent model, and we provide a refined generalization analysis of the gradient descent method for two-layer networks with smooth activations. A remarkable point of this study is that our generalization bound has much better dependence on the network width compared to existing results. As a result, our theory significantly enlarges a class of over-parameterized networks having provable generalization ability, with respect to network width, while most studies require much higher over-parameterization.

Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions can be answered with a single hop if they target specific entity types, or the facts needed to answer them are redundant. Our analysis is centered on HotpotQA, where we show that single-hop reasoning can solve much more of the dataset than previously thought. We introduce a single-hop BERT-based RC model that achieves 67 F1---comparable to state-of-the-art multi-hop models. We also design an evaluation setting where humans are not shown all of the necessary paragraphs for the intended multi-hop reasoning but can still answer over 80% of questions. Together with detailed error analysis, these results suggest there should be an increasing focus on the role of evidence in multi-hop reasoning and possibly even a shift towards information retrieval style evaluations with large and diverse evidence collections.

The world produces about 2.5 quintillion bytes of data every day. Storing and transferring all of this enormous--and constantly growing--number of images, videos, Tweets, and other forms of data is becoming a significant challenge, one that threatens to undermine the growth of the internet and thwart the introduction of new technologies, such as the Internet of Things. Now, a team of researchers reports that an algorithm that uses a machine learning technique based on the human brain could ease that data clog by reducing the size of multimedia files, such as videos and images, and restoring them without losing much quality or information. Machine learning is a type of artificial intelligence, or AI. In a study, the researchers developed an algorithm that features a recurrent neural network to compress and restore data, according to C. Lee Giles, David Reese Professor of Information Sciences and Technology, Penn State, and an Institute for CyberScience associate.