The task of Question Answering has gained prominence in the past few decades for testing the ability of machines to understand natural language. Large datasets for Machine Reading have led to the development of neural models that cater to deeper language understanding compared to information retrieval tasks. Different components in these neural architectures are intended to tackle different challenges. As a first step towards achieving generalization across multiple domains, we attempt to understand and compare the peculiarities of existing end-to-end neural models on the Stanford Question Answering Dataset (SQuAD) by performing quantitative as well as qualitative analysis of the results attained by each of them. We observed that prediction errors reflect certain model-specific biases, which we further discuss in this paper.

This survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language. We categorize the information flow in multimodal processing with respect to cognitive models of human information processing and analyze different methods for combining multimodal representations. Based on this methodological inventory, we discuss the benefit of multimodal grounding for a variety of language processing tasks and the challenges that arise. We particularly focus on multimodal grounding of verbs which play a crucial role for the compositional power of language.

Artificial intelligence is transforming the legal profession -- and that includes legal ethics. AI and similar cutting-edge technologies raise many complex ethical issues and challenges that lawyers ignore at their peril. At the same time, AI also holds out the promise of helping lawyers to meet their ethical obligations, serve their clients more effectively, and promote access to justice and the rule of law. What does AI mean for legal ethics, what should lawyers do to prepare for these changes, and how could AI help improve the legal profession? In some ways, nothing has changed.

As machine learning and artificial intelligence pervade the computing environment, the drive for better hardware resources is increasing significantly. Although computational hardware is optimised to its best, it needs to be the perfect fit for ML applications. With a plethora of devices available in the market -- multi-core processors, large cloud-based databases -- it is often tough to choose them to serve the exact ML purpose. One such hardware component that has picked up popularity in recent times is the accelerator. The accelerators are a class of microprocessors which are designed specifically to serve AI and ML related tasks.

Due to recent advances - compute, data, models - the role of learning in autonomous systems has expanded significantly, rendering new applications possible for the first time. While some of the most significant benefits are obtained in the perception modules of the software stack, other aspects continue to rely on known manual procedures based on prior knowledge on geometry, dynamics, kinematics etc. Nonetheless, learning gains relevance in these modules when data collection and curation become easier than manual rule design. Building on this coarse and broad survey of current research, the final sections aim to provide insights into future potentials and challenges as well as the necessity of structure in current practical applications.

It is undeniable that Artificial Intelligence (AI) and blockchain are two of the major technologies that are driving the pace of innovation and introducing radical shifts in rapidly growing list of industries. As Artificial Intelligence advances, the need for enhanced security is becoming apparent and therefore Blockchain is becoming more common in the market. Leaders in tech are more and more infusing the two cutting edge technologies to create innovative products and increase efficiencies. One of the factors driving this trend is the nature of the two technologies as they work well together hand in hand. It's projected that Blockchain and AI will eventually become inseparable as intelligent platforms evolve and become more mainstream.

Check out the full schedule for the AI Conference in London, October 8-11, 2018. Hurry--best price ends July 13. In this post, I share slides and notes from a talk Roger Chen and I gave in May 2018 at the Artificial Intelligence Conference in New York. Most companies are beginning to explore how to use machine learning and AI, and we wanted to give an overview and framework for how to think about these technologies and their roles in automation. Along the way, we describe the machine learning and AI tools that can be used to enable automation.

DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio--textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not include a POI name or its semantically coherent variations, respectively. By leveraging the proportion of POI-relevant and POI-irrelevant tweets, the proposed algorithm demonstrates much higher clustering performance than the DBSCAN case in terms of $\mathcal{F}_1$ score and its variants. While DBSTexC performs exactly as DBSCAN with the textually homogeneous inputs, it far outperforms DBSCAN with the textually heterogeneous inputs. Furthermore, to further improve the clustering quality by fully capturing the geographic distribution of tweets, we present fuzzy DBSTexC (F-DBSTexC), an extension of DBSTexC, which incorporates the notion of fuzzy clustering into the DBSTexC. We then demonstrate the robustness of F-DBSTexC via intensive experiments. The computational complexity of our algorithms is also analytically and numerically shown.

Many data mining tasks cannot be completely addressed by automated processes, such as sentiment analysis and image classification. Crowdsourcing is an effective way to harness the human cognitive ability to process these machine-hard tasks. Thanks to public crowdsourcing platforms, e.g., Amazon Mechanical Turk and CrowdFlower, we can easily involve hundreds of thousands of ordinary workers (i.e., the crowd) to address these machine-hard tasks. In this tutorial, we will survey and synthesize a wide spectrum of existing studies on crowd-powered data mining. We first give an overview of crowdsourcing, and then summarize the fundamental techniques, including quality control, cost control, and latency control, which must be considered in crowdsourced data mining. Next we review crowd-powered data mining operations, including classification, clustering, pattern mining, outlier detection, knowledge base construction and enrichment. Finally, we provide the emerging challenges in crowdsourced data mining.

For many modern applications in science and engineering, data are collected in a streaming fashion carrying time-varying information, and practitioners need to process them with a limited amount of memory and computational resources in a timely manner for decision making. This often is coupled with the missing data problem, such that only a small fraction of data attributes are observed. These complications impose significant, and unconventional, constraints on the problem of streaming Principal Component Analysis (PCA) and subspace tracking, which is an essential building block for many inference tasks in signal processing and machine learning. This survey article reviews a variety of classical and recent algorithms for solving this problem with low computational and memory complexities, particularly those applicable in the big data regime with missing data. We illustrate that streaming PCA and subspace tracking algorithms can be understood through algebraic and geometric perspectives, and they need to be adjusted carefully to handle missing data. Both asymptotic and non-asymptotic convergence guarantees are reviewed. Finally, we benchmark the performance of several competitive algorithms in the presence of missing data for both well-conditioned and ill-conditioned systems.