In this paper we address the problem of discovering a small set of frequent serial episodes from sequential data so as to adequately characterize or summarize the data. We discuss an algorithm based on the Minimum Description Length (MDL) principle and the algorithm is a slight modification of an earlier method, called CSC-2. We present a novel generative model for sequence data containing prominent pairs of serial episodes and, using this, provide some statistical justification for the algorithm. We believe this is the first instance of such a statistical justification for an MDL based algorithm for summarizing event sequence data. We then present a novel application of this data mining algorithm in text classification. By considering text documents as temporal sequences of words, the data mining algorithm can find a set of characteristic episodes for all the training data as a whole. The words that are part of these characteristic episodes could then be considered the only relevant words for the dictionary thus resulting in a considerably reduced feature vector dimension. We show, through simulation experiments using benchmark data sets, that the discovered frequent episodes can be used to achieve more than four-fold reduction in dictionary size without losing any classification accuracy.

Statistical approaches to processing natural language text have become dominant during the recent years. This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear. This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. This course explains why predictive analytics projects are ultimately classification problems, and how data scientists can choose the right strategy for their projects. This book covers the field of machine learning, which is the study of algorithms that allow computer programs to automatically improve through experience.

Graph kernels have become an established and widely-used technique for solving classification tasks on graphs. This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years. We describe and categorize graph kernels based on properties inherent to their design, such as the nature of their extracted graph features, their method of computation and their applicability to problems in practice. In an extensive experimental evaluation, we study the classification accuracy of a large suite of graph kernels on established benchmarks as well as new datasets. We compare the performance of popular kernels with several baseline methods and study the effect of applying a Gaussian RBF kernel to the metric induced by a graph kernel. In doing so, we find that simple baselines become competitive after this transformation on some datasets. Moreover, we study the extent to which existing graph kernels agree in their predictions (and prediction errors) and obtain a data-driven categorization of kernels as result. Finally, based on our experimental results, we derive a practitioner's guide to kernel-based graph classification.

Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated with each class. This semantic-descriptor space is generally shared by both seen and unseen categories. However, ZSL suffers from hubness, domain discrepancy and biased-ness towards seen classes. To tackle these problems, we propose a three-step approach to zero-shot learning. Firstly, a mapping is learned from the semantic-descriptor space to the image-feature space. This mapping learns to minimize both one-to-one and pairwise distances between semantic embeddings and the image features of the corresponding classes. Secondly, we propose test-time domain adaptation to adapt the semantic embedding of the unseen classes to the test data. This is achieved by finding correspondences between the semantic descriptors and the image features. Thirdly, we propose scaled calibration on the classification scores of the seen classes. This is necessary because the ZSL model is biased towards seen classes as the unseen classes are not used in the training. Finally, to validate the proposed three-step approach, we performed experiments on four benchmark datasets where the proposed method outperformed previous results. We also studied and analyzed the performance of each component of our proposed ZSL framework.

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information about the model is released except its final decision. Such decision-based attacks usually require lots of queries, while real-world image recognition systems might actually restrict the number of queries. In this paper, we propose qFool, a novel decision-based attack algorithm that can generate adversarial examples using a small number of queries. The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples. We also enhance our method by constraining adversarial perturbations in low-frequency subspace, which can make qFool even more computationally efficient. Altogether, we manage to fool commercial image recognition systems with a small number of queries, which demonstrates the actual effectiveness of our new algorithm in practice.

AI and machine learning are breathing new life and business opportunities into that tired old phrase, "automating paper-based processes." I saw an example of how software developers can inject intelligence into business processes in this VIDEO interview at SAP TechEd with Dr. Matthias Sessler, technical enablement lead, SAP Leonardo Machine Learning Foundation. The demo showed image object detection combined with scene text recognition and optical character recognition (OCR), three of the 23 ready-to-use services on offer from the SAP Leonardo Machine Learning Foundation. Image object detection automatically identifies objects from images like a bus, and often tag teams with scene text recognition, which reads the fine print, such as the station name and line number. "With smartphones, it's so much easier for people to take a picture of something. However, developers need a toolbox so they can quickly build machine learning capabilities to make sense of these images and text," said Sessler.

The world is highly competitive and is high paced. There is increased tension to reduce operational costs, rework and time wastage. Artificial Intelligence (AI) is the right technology for these requirements. Every industry uses AI to analyze the data from sensors, historical data for understanding the industry output and input patterns thereby improving the productivity. System failure or machine failure is unavoidable in any industry.

AI and machine learning are breathing new life and business opportunities into that tired old phrase, "automating paper-based processes." I saw an example of how software developers can inject intelligence into business processes in this VIDEO interview at SAP TechEd with Dr. Matthias Sessler, technical enablement lead, SAP Leonardo Machine Learning Foundation. The demo showed image object detection combined with scene text recognition and optical character recognition (OCR), three of the 23 ready-to-use services on offer from the SAP Leonardo Machine Learning Foundation. Image object detection automatically identifies objects from images like a bus, and often tag teams with scene text recognition, which reads the fine print, such as the station name and line number. "With smartphones, it's so much easier for people to take a picture of something. However, developers need a toolbox so they can quickly build machine learning capabilities to make sense of these images and text," said Sessler.

TELLING a yellow taxi and a pair of binoculars apart is so easy most people could do it standing on their head. Not so for an artificial intelligence: flip the cab upside down and it sees binoculars. This is just one of dozens of examples that show AI is a lot worse at identifying objects by sight than many people realise.

WhatsApp appears to be working on a new feature to help users identify whether an image they receive is legitimate or not. While picking apart update 2.19.73, WABetaInfo discovered a "search by image" function that will let you upload a received image directly to Google to reveal "similar or equal" images on the web. With this info, you should be able to more accurately judge whether the picture is real, or fake news. The feature isn't available yet, and there's no official word on when it will be.