The tragic school shootings of recent years have led to a great deal of discussion around "hardening" K-12 schools to gun violence. And, the concept of "hardening" usually conjures visions of metal detectors, armed guards, active shooter drills and any number of bullet-proof products, from windows to white boards. Truly hardening a K-12 school system from gun violence, however, requires a more nuanced approach. First of all, disrupting the normal flow of education with pat-downs and other intrusive activity can have a detrimental effect on students by instilling the notion that they are constantly in danger, or that the school perceives them as a threat. The tradeoffs between security and the student experience need to be considered, particularly when it involves introducing more stress on kids who already have to spend too much of their childhood participating in active shooter drills.

This course is for informational purpose only. Its goal is to introduce machine learning to beginners. Machine learning differs from conventional programming (no need to give specific step by step control flow instruction). The model learns by updating weights. Different models have different architecture elements.

The premature adoption of inadequate technologies can often do more harm than good. One of the most apposite examples is the frequently misguided espousal of basic ChatBot solutions in an increasingly digital-first landscape. ChatBots have been around for a long time, having grown from Interactive Voice Response (IVR) systems from over 20 years ago. But with businesses progressively shifting online over the past few years (in particular the past 18 months), organizations everywhere have been on the hunt searching for solutions that can reduce the volume of costly, time-consuming digital interactions with customers. Yet traditional ChatBots have infamously underperformed in terms of user experience. More often than not, these Bots will continue to pass a query to an employee when the task at hand becomes too difficult -- only serving to complicate the customer experience, rather than enhance it.

By this summer, Martine had her dating ritual figured out. It was a series of small actions that changed the mood in her Queens bedroom, so that she could contemplate making flirtatious chit-chat from the same space that she'd been using to perform her sales job, take online classes, exercise, and sleep. "I'd turn off everything," she told me. She'd sit on her floor, cross-legged, and meditate for twenty minutes. Next, she'd pull out her essential oils, open a bottle of something nice, lavender or peppermint, and take a sniff.

Federated learning (FL) is a distributed machine learning approach involving multiple clients collaboratively training a shared model. Such a system has the advantage of more training data from multiple clients, but data can be non-identically and independently distributed (non-i.i.d.). Privacy and integrity preserving features such as differential privacy (DP) and robust aggregation (RA) are commonly used in FL. In this work, we show that on common deep learning tasks, the performance of FL models differs amongst clients and situations, and FL models can sometimes perform worse than local models due to non-i.i.d. data. Secondly, we show that incorporating DP and RA degrades performance further. Then, we conduct an ablation study on the performance impact of different combinations of common personalization approaches for FL, such as finetuning, mixture-of-experts ensemble, multi-task learning, and knowledge distillation. It is observed that certain combinations of personalization approaches are more impactful in certain scenarios while others always improve performance, and combination approaches are better than individual ones. Most clients obtained better performance with combined personalized FL and recover from performance degradation caused by non-i.i.d. data, DP, and RA.

Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-trivial. Despite the pervasiveness of spoken dialog, automated speech understanding and quality information extraction remains markedly poor, especially when compared to written prose. Furthermore, compared to understanding text, auditory communication poses many additional challenges such as speaker disfluencies, informal prose styles, and lack of structure. These concerns all demonstrate the need for a distinctly speech tailored interactive system to help users understand and navigate the spoken language domain. While individual automatic speech recognition (ASR) and text summarization methods already exist, they are imperfect technologies; neither consider user purpose and intent nor address spoken language induced complications. Consequently, we design a two stage ASR and text summarization pipeline and propose a set of semantic segmentation and merging algorithms to resolve these speech modeling challenges. Our system enables users to easily browse and navigate content as well as recover from errors in these underlying technologies. Finally, we present an evaluation of the system which highlights user preference for hierarchical summarization as a tool to quickly skim audio and identify content of interest to the user.

One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the analysis of an agent assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user queries about its execution of sequences of actions. We show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable causal model of the system in stationary, fully observable, and deterministic settings. We also introduce dynamic causal decision networks (DCDNs) that capture the causal structure of STRIPS-like domains. A comparative analysis of different classes of queries is also presented in terms of the computational requirements needed to answer them and the efforts required to evaluate their responses to learn the correct model.

The ubiquitous availability of computing devices and the widespread use of the internet have generated a large amount of data continuously. Therefore, the amount of available information on any given topic is far beyond humans' processing capacity to properly process, causing what is known as information overload. To efficiently cope with large amounts of information and generate content with significant value to users, we require identifying, merging and summarising information. Data summaries can help gather related information and collect it into a shorter format that enables answering complicated questions, gaining new insight and discovering conceptual boundaries. This thesis focuses on three main challenges to alleviate information overload using novel summarisation techniques. It further intends to facilitate the analysis of documents to support personalised information extraction. This thesis separates the research issues into four areas, covering (i) feature engineering in document summarisation, (ii) traditional static and inflexible summaries, (iii) traditional generic summarisation approaches, and (iv) the need for reference summaries. We propose novel approaches to tackle these challenges, by: i)enabling automatic intelligent feature engineering, ii) enabling flexible and interactive summarisation, iii) utilising intelligent and personalised summarisation approaches. The experimental results prove the efficiency of the proposed approaches compared to other state-of-the-art models. We further propose solutions to the information overload problem in different domains through summarisation, covering network traffic data, health data and business process data.

As Artificial Intelligence (AI) is used in more applications, the need to consider and mitigate biases from the learned models has followed. Most works in developing fair learning algorithms focus on the offline setting. However, in many real-world applications data comes in an online fashion and needs to be processed on the fly. Moreover, in practical application, there is a trade-off between accuracy and fairness that needs to be accounted for, but current methods often have multiple hyperparameters with non-trivial interaction to achieve fairness. In this paper, we propose a flexible ensemble algorithm for fair decision-making in the more challenging context of evolving online settings. This algorithm, called FARF (Fair and Adaptive Random Forests), is based on using online component classifiers and updating them according to the current distribution, that also accounts for fairness and a single hyperparameters that alters fairness-accuracy balance. Experiments on real-world discriminated data streams demonstrate the utility of FARF.

Artificial Intelligence is the process of re-creating human knowledge in robots that are designed to think and act like humans. AI has evolved from a once-obscure technology into a standard toolbox for software development and design. Without a question, Artificial Intelligence (AI) is the future of automation. Robotization, DevOps phases, the Internet Chabot, and mechanical technology are all examples of upcoming IT advancements using Artificial Intelligence. Artificial Intelligence Jobs is a fast-paced, high-risk industry that is rapidly infiltrating our daily lives.