This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed.

Anomaly detection aims to recognize samples with anomalous and unusual patterns with respect to a set of normal data, which is significant for numerous domain applications, e.g. in industrial inspection, medical imaging, and security enforcement. There are two key research challenges associated with existing anomaly detention approaches: (1) many of them perform well on low-dimensional problems however the performance on high-dimensional instances is limited, such as images; (2) many of them depend on often still rely on traditional supervised approaches and manual engineering of features, while the topic has not been fully explored yet using modern deep learning approaches, even when the well-label samples are limited. In this paper, we propose a One-for-all Image Anomaly Detection system (OIAD) based on disentangled learning using only clean samples. Our key insight is that the impact of small perturbation on the latent representation can be bounded for normal samples while anomaly images are usually outside such bounded intervals, called structure consistency. We implement this idea and evaluate its performance for anomaly detention. Our experiments with three datasets show that OIAD can detect over $90\%$ of anomalies while maintaining a high low false alarm rate. It can also detect suspicious samples from samples labeled as clean, coincided with what humans would deem unusual.

Newark Venture Partners hosted a full house at its biannual Demo Day, for its 7th NVP Labs class, at the Audible Innovation Cathedral. The event featured presentations from founders of the graduating companies, Botmock, Brahmin Solutions, Galaxy.AI, MindRight Health, omniX, Speak2 Software and SpeechKit. Other featured speakers included Don Katz, Founder and Executive Chairman of Audible, Newark Assemblywoman Eliana Pintor Marin, and Wole Coaxum, Founder and CEO of MoCaFi (an NVP portfolio company) who paid tribute to Dr. Martin Luther King, Jr.'s birthday. Don Katz, Founder and Executive Chairman of Audible said, "Everyone loves a comeback story and Newark has a great one, including Newark Venture Partners, which is an internationally acknowledged phenomenon that has exceeded all of my founder expectations. When I recently visited NVP labs I was dazzled by one impassioned founder, team, and company after another. Now it is time to double down on NVP's measurable success."

KHARAGPUR: Researchers at IIT Kharagpur have evolved an Artificial Intelligence-aided method to automate the reading of legal case judgments, the premier institute said in a statement on Friday. The researchers from IIT Kharagpur's Computer Science and Engineering department have developed two deep neural models to understand the rhetorical roles of sentences in a legal case judgment, which could prove phenomenal in India where AI is yet to sufficiently penetrate the legal field. The country uses a Common Law system that prioritises the doctrine of legal precedent over statutory law, and where legal documents are often written in an unstructured way. "Taking 50 judgments from the Supreme Court of India, we segmented these by first labelling sentences with the help of three senior law students from IIT Kharagpur's Rajiv Gandhi School of Intellectual Property Law, then performing extensive analysis of the human-assigned labels and developing a high quality gold standard corpus to train the machine to carry out the task," explained research lead Professor Saptarshi Ghosh. Unlike earlier attempts which required substantial human intervention, the neural methods used by Ghosh's team enables automatic learning of the features, given sufficient amount of data, and can be used across multiple legal domains.

In October 2018, months after a brief reveal, Amazon brought Whisper Mode to select third- and first-party Alexa devices. It expanded the feature to all locales in November 2019, such that all smart home appliances powered by Alexa -- the company's virtual assistant -- now respond to whispered speech by whispering back. Amazon was a bit light on the technical details initially, save that Whisper Mode uses a neural network -- layers of mathematical functions loosely modeled after the human brain's neurons -- to distinguish among normal and whispered words. But in an academic paper appearing in the January 2020 issue of the journal IEEE Signal Processing Letters and an accompanying blog post, it detailed the research that led to the expansion. The principal challenge was converting normal speech into whispered speech while maintaining naturalness and speaker identity, explained Marius Cotescu, an applied scientist in Amazon's text-to-speech research group.

Data augmentation is essential for medical research to increase the size of training datasets and achieve better results. In this work, we experiment three GAN architectures with different loss functions to generate new brain MRIs. The results show the importance of hyperparameter tuning and the use of mini-batch similarity layer in the Discriminator and gradient penalty in the loss function to achieve convergence with high quality and realism. Moreover, huge computation time is needed to generate indistinguishable images from the original dataset.

The Mixed-Membership Stochastic Blockmodel~(MMSB) is proposed as one of the state-of-the-art Bayesian relational methods suitable for learning the complex hidden structure underlying the network data. However, the current formulation of MMSB suffers from the following two issues: (1), the prior information~(e.g. entities' community structural information) can not be well embedded in the modelling; (2), community evolution can not be well described in the literature. Therefore, we propose a non-parametric fragmentation coagulation based Mixed Membership Stochastic Blockmodel (fcMMSB). Our model performs entity-based clustering to capture the community information for entities and linkage-based clustering to derive the group information for links simultaneously. Besides, the proposed model infers the network structure and models community evolution, manifested by appearances and disappearances of communities, using the discrete fragmentation coagulation process (DFCP). By integrating the community structure with the group compatibility matrix we derive a generalized version of MMSB. An efficient Gibbs sampling scheme with Polya Gamma (PG) approach is implemented for posterior inference. We validate our model on synthetic and real world data.

Cybersecurity attacks are growing both in frequency and sophistication over the years. This increasing sophistication and complexity call for more advancement and continuous innovation in defensive strategies. Traditional methods of intrusion detection and deep packet inspection, while still largely used and recommended, are no longer sufficient to meet the demands of growing security threats. As computing power increases and cost drops, Machine Learning is seen as an alternative method or an additional mechanism to defend against malwares, botnets, and other attacks. This paper explores Machine Learning as a viable solution by examining its capabilities to classify malicious traffic in a network. First, a strong data analysis is performed resulting in 22 extracted features from the initial Netflow datasets. All these features are then compared with one another through a feature selection process. Then, our approach analyzes five different machine learning algorithms against NetFlow dataset containing common botnets. The Random Forest Classifier succeeds in detecting more than 95% of the botnets in 8 out of 13 scenarios and more than 55% in the most difficult datasets. Finally, insight is given to improve and generalize the results, especially through a bootstrapping technique.

As the field of Spoken Dialogue Systems and Conversational AI grows, so does the need for tools and environments that abstract away implementation details in order to expedite the development process, lower the barrier of entry to the field, and offer a common test-bed for new ideas. In this paper, we present Plato, a flexible Conversational AI platform written in Python that supports any kind of conversational agent architecture, from standard architectures to architectures with jointly-trained components, single- or multi-party interactions, and offline or online training of any conversational agent component. Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.

Most insurance companies depend on human expertise and business rules-based software to protect themselves from fraud. And the drive for digital transformation and process automation means data and scenarios change faster than you can update the rules. Machine learning has the potential to allow insurers to move from the current state of "detect and react" to "predict and prevent." It excels at automating the process of taking large volumes of data, analysing multiple fraud indicators in parallel – which taken individually may often be quite normal – and finding potential fraud. Generally, there are two ways to teach or train a machine learning algorithm, which depend on the available data: supervised and unsupervised learning.