The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian matrix. In particular, we examine how important the negative eigenvalues are and the benefits one can observe in handling them appropriately.

Gait is a person's natural walking style and a complex biological process that is unique to each person. Recently, the channel state information (CSI) of WiFi devices have been exploited to capture human gait biometrics for user identification. However, the performance of existing CSI-based gait identification systems is far from satisfactory. They can only achieve limited identification accuracy (maximum $93\%$) only for a very small group of people (i.e., between 2 to 10). To address such challenge, an end-to-end deep CSI learning system is developed, which exploits deep neural networks to automatically learn the salient gait features in CSI data that are discriminative enough to distinguish different people Firstly, the raw CSI data are sanitized through window-based denoising, mean centering and normalization. The sanitized data is then passed to a residual deep convolutional neural network (DCNN), which automatically extracts the hierarchical features of gait-signatures embedded in the CSI data. Finally, a softmax classifier utilizes the extracted features to make the final prediction about the identity of the user. In a typical indoor environment, a top-1 accuracy of $97.12 \pm 1.13\%$ is achieved for a dataset of 30 people.

Machine learning models or algorithms have shown over the past few years that they can exhibit human traits like racism and sexism by misidentifying black people as gorillas (Barr, 2015) or perpetuating gender income inequality through ad suggestions (Datta et al., 2015). Algorithmic bias, however, is not inherently problematic. Given the potential harm machine learning can cause, how can South African organisations mitigate against problematic algorithmic bias in their data and models? This essay will use the taxonomy of algorithmic bias created by Danks and London (2017) to differentiate between the various types of algorithmic bias and give examples of how problematic bias might perpetuate immoral discrimination within a South African context. Specifically, it will examine training data bias, algorithmic focus bias and transfer context bias. The most intuitive bias is training data bias; if biased data are used, the resulting model reflects that bias.

Alphabet, the parent company of the internet search giant Google, earned $39.27bn in the last three months of 2018, but its share price sank as its costs rose. Alphabet's revenues for the quarter were 22% higher than the same period last year and the company made a profit of $8.9bn, the company announced on Monday. Revenues in the US rose 20% while revenues from Europe, the Middle East and Africa rose 29%, helped by the strength of the euro and the pound. It was the latest tech company to announce strong revenue growth – news that has cheered investors – but rising costs that come as the company is facing increasing competition from Amazon clouded the news. The fees that Alphabet pays to companies like Apple for Google to be their default search engine rose to $7.4bn up from $6.6bn for the same period last year.

This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and issues are expressed in this Report. The Report encapsulates the history of computer science efforts to create systems that explain and instruct (intelligent tutoring systems and expert systems). The Report expresses the explainability issues and challenges in modern AI, and presents capsule views of the leading psychological theories of explanation. Certain articles stand out by virtue of their particular relevance to XAI, and their methods, results, and key points are highlighted. It is recommended that AI/XAI researchers be encouraged to include in their research reports fuller details on their empirical or experimental methods, in the fashion of experimental psychology research reports: details on Participants, Instructions, Procedures, Tasks, Dependent Variables (operational definitions of the measures and metrics), Independent Variables (conditions), and Control Conditions.

At some point last year, Google's constant requests to prove I'm human began to feel increasingly aggressive. More and more, the simple, slightly too-cute button saying "I'm not a robot" was followed by demands to prove it -- by selecting all the traffic lights, crosswalks, and storefronts in an image grid. Soon the traffic lights were buried in distant foliage, the crosswalks warped and half around a corner, the storefront signage blurry and in Korean. There's something uniquely dispiriting about being asked to identify a fire hydrant and struggling at it. These tests are called CAPTCHA, an acronym for Completely Automated Public Turing test to tell Computers and Humans Apart, and they've reached this sort of inscrutability plateau before. In the early 2000s, simple images of text were enough to stump most spambots.

Despite recent setbacks, solar remains a bright spot in the often wobbly renewable energy sector. In the U.S., the solar market is projected to top $22.90 billion by 2025, driven by falling materials costs and growing interest in offsite and rooftop installations. Moreover, in China -- the world's leading installer of solar panels and the largest producer of photovoltaic power -- 1.84 percent of the total electricity generated in the country two years ago came from solar. There's clearly growth -- which San Francisco startup Aurora Solar seeks to capitalize on with a novel solution combining lidar data, computer-assisted design, and computer vision. The company, which develops a suite of software that streamlines the solar panel installation process, today announced it has secured $20 million in a Series A round of financing from Energize Ventures, with contributions from S28 Capital and existing investor Pear.

Staff scheduling is a universal problem that can be encountered in many organizations, such as call centers, educational institution, industry, hospital, and any other public services. It is one of the most important aspects of workforce management strategy and the one that is most prone to errors or issues as there are many entities should be considered, such as the staff turnover, employee availability, time between rotations, unusual periods of activity, and even the last-minute shift changes. The nurse scheduling problem is a variant of staff scheduling problems which appoints nurses to shifts as well as rooms per day taking both hard constraints, i.e., hospital requirements, and soft constraints, i.e., nurse preferences, into account. Most algorithms used for scheduling problems fall short when it comes to the number of inputs they can handle. In this paper, constraint programming was developed to solve the nurse scheduling problem. The developed constraint programming model was then implemented using python programming language.

Digital Adherence Technologies (DATs) are an increasingly popular method for verifying patient adherence to many medications. We analyze data from one city served by 99DOTS, a phone-call-based DAT deployed for Tuberculosis (TB) treatment in India where nearly 3 million people are afflicted with the disease each year. The data contains nearly 17,000 patients and 2.1M phone calls. We lay the groundwork for learning from this real-world data, including a method for avoiding the effects of unobserved interventions in training data used for machine learning. We then construct a deep learning model, demonstrate its interpretability, and show how it can be adapted and trained in three different clinical scenarios to better target and improve patient care. In the real-time risk prediction setting our model could be used to proactively intervene with 21% more patients and before 76% more missed doses than current heuristic baselines. For outcome prediction, our model performs 40% better than baseline methods, allowing cities to target more resources to clinics with a heavier burden of patients at risk of failure. Finally, we present a case study demonstrating how our model can be trained in an end-to-end decision focused learning setting to achieve 15% better solution quality in an example decision problem faced by health workers.

The idea of'Automata' originates from the mythologies of many cultures across the globe. Early inventors and engineers from ancient civilisation such as Greek, Chinese or Ptolemaic Egyptian attempted to develop a self-operating or automated machine resembling humans and animals. The term'Robot' comes from the Czech word "Robota" refers to "Forced Work or Labor" which was first used to refer the word'Artificial Automata' in a 1920 play R.U.R (Rossum's Universal Robots) by the Czech interwar writer'Karl Capek.' In 1928, one of the first'Humanoid Robots' invented by W.H.Richards, delivered a speech in the annual event of the'Model Engineers Society' in London. The brief history shows that'Robots' are not a new innovation but is a'Thinking Machine' which is programmed by a computer and is capable of doing complex series' of actions automatically.