With the proliferation of social media platforms and e-commerce sites, several cross-domain collaborative filtering strategies have been recently introduced to transfer the knowledge of user preferences across domains. The main challenge of cross-domain recommendation is to weigh and learn users' different behaviors in multiple domains. In this paper, we propose a Cross-Domain collaborative filtering model following a Translation-based strategy, namely CDT. In our model, we learn the embedding space with translation vectors and capture high-order feature interactions in users' multiple preferences across domains. In doing so, we efficiently compute the transitivity between feature latent embeddings, that is if feature pairs have high interaction weights in the latent space, then feature embeddings with no observed interactions across the domains will be closely related as well. We formulate our objective function as a ranking problem in factorization machines and learn the model's parameters via gradient descent. In addition, to better capture the non-linearity in user preferences across domains we extend the proposed CDT model by using a deep learning strategy, namely DeepCDT. Our experiments on six publicly available cross-domain tasks demonstrate the effectiveness of the proposed models, outperforming other state-of-the-art cross-domain strategies.

Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations e.g. the Kalman Filter. However, they require significant domain knowledge to derive the parametric form and considerable hand-tuning to correctly set all the parameters. Data driven techniques e.g. Recurrent Neural Networks have emerged as compelling alternatives to SSMs with wide success across a number of challenging tasks, in part due to their ability to extract relevant features from rich inputs. They however lack interpretability and robustness to unseen conditions. In this work, we present DynaNet, a hybrid deep learning and time-varying state-space model which can be trained end-to-end. Our neural Kalman dynamical model allows us to exploit the relative merits of each approach. We demonstrate state-of-the-art estimation and prediction on a number of physically challenging tasks, including visual odometry, sensor fusion for visual-inertial navigation and pendulum control. In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).

W e tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper . In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via lookup tables. W e demonstrate the exceptional advantage of our scheme over existing quantization approaches on several datasets of visual descriptors via outperforming the previous state-of-the-art by a large margin.

Anomaly detection is a fundamental problem in data mining field with many real-world applications. A vast majority of existing anomaly detection methods predominately focused on data collected from a single source. In real-world applications, instances often have multiple types of features, such as images (ID photos, finger prints) and texts (bank transaction histories, user online social media posts), resulting in the so-called multi-modal data. In this paper, we focus on identifying anomalies whose patterns are disparate across different modalities, i.e., cross-modal anomalies. Some of the data instances within a multi-modal context are often not anomalous when they are viewed separately in each individual modality, but contains inconsistent patterns when multiple sources are jointly considered. The existence of multi-modal data in many real-world scenarios brings both opportunities and challenges to the canonical task of anomaly detection. On the one hand, in multi-modal data, information of different modalities may complement each other in improving the detection performance. On the other hand, complicated distributions across different modalities call for a principled framework to characterize their inherent and complex correlations, which is often difficult to capture with conventional linear models. To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data. Experiments on real-world datasets demonstrate the effectiveness of the proposed framework comparing with the state-of-the-art.

Unlike task-specific algorithms, Deep Learning is a part of Machine Learning family based on learning data representations. With massive amounts of computational power, machines can now recognize objects and translate speech in real time, enabling a smart Artificial intelligence in systems. The concept of a software simulating the neocortex's large array of neurons in an artificial neural network is decades old, and it has led to as many disappointments as breakthroughs. But because of improvements in mathematical formulas and increasingly powerful computers, today researchers & data scientists can model many more layers of virtual neurons than ever before. "Recent improvements in Deep Learning has reignited some of the grand challenges in Artificial Intelligence."

In the aftermath of a natural disaster, response and recovery efforts can be drastically slowed down by manual data collection. Traditionally, insurance assessors and government officials have to rely on human interpretation of imagery and site visits to assess damage and loss. But depending on the scope of a disaster, this necessary process could delay relief to disaster victims. Article Snapshot: At this year's Esri User Conference plenary session, the United Services Automobile Association (USAA) demonstrated the use of deep learning capabilities in ArcGIS to perform automated damage assessment of homes after the devastating Woolsey fire. This work was a collaborative prototype between Esri and USAA to show the art of the possible in doing this type of damage assessment using the ArcGIS platform.

Decades before today's deep learning neural networks compiled imponderable layers of statistics into working machines, researchers were trying to figure out how one explains statistical findings to a human. IBM this week offered up the latest effort in that long quest to interpret, explain, and justify machine learning, a set of open-source programming resources it calls "AI 360 Explainability." It remains to be seen whether yet another tool will solve the conundrum of how people can understand what is going on when artificial intelligence makes a prediction based on data. The toolkit consists of eight different algorithms released in the course of 2018. The IBM tools are posted on Github as a Python library.

I should have taken heed of the Socratic paradox that'all I know is that I do not know anything', as in January of 2016, I publicly expressed to the scientific and medical community that'There are certain things that a human brain does much better than any piece of technology – such as solving a crossword puzzle or playing the game Go.' In January of 2016, I was in lofty company, as the majority of the big brains of Artificial Intelligence (AI) felt that it would take at least 50 years for a computer to beat any human at Go. Three months later the Google DeepMind Alpha Go system did just that, when it beat not any average human Go player – but the world's 18-time world Go champion, Lee Sedol. This is a non-trivial occurrence. Because there are many tasks that are performed in healthcare each day by humans, that are well suited to be better performed by intelligent thinking machines. For example, the foundation of healthcare – the diagnosis, consists of pattern recognition and algorithms, both of which are superior strengths of machine over humans. My take away from this is that the changes are occurring much more quickly than I realised, not only in the development of AI, but in many other areas such as the global dispersion of high-speed connectivity, blockchain, plummeting costs of data storage, and tremendous improvements in biosensors of all shapes and sizes. The future that many felt was at least 50 years away, appears to already be behind us – and these powerful thinking machines will not stand alone, but will play a central role in our increasing global connectivity.

Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images.

TEACH ME AND I REMEMBER. Life is a journey through learning experiences. As, we are continuously learning new tasks and acquiring new knowledge and we have a magical, and purely understood ability to leverage previous experiences to optimize how we build new knowledge. Learning never stops and it shapes as intellectual and social beings. Could we recreate the continuity of learning in artificial intelligence(AI) models.