Are you interested in machine learning? Then, this course is right for you! This course is designed by two professional data scientists so that we can share our knowledge and help you easily learn complex theories, algorithms and coding libraries. Take you step by step into the world of machine learning. In each tutorial, you will develop new skills and improve your understanding of the challenging but lucrative part of data science.

A global shortage of one crucial piece of technology is causing delays in everything from cars and televisions to video game consoles and Australia's National Broadband Network rollout. A temporary shutdown in the production of silicon computer chips at the start of the coronavirus pandemic, as well as severe storms in Texas causing more recent delays, has caused worldwide chip shortages, with a knock-on effect for the production of phones, laptops and even automobiles. Samsung, which is the largest manufacturer of computer chips in the world, as well as one of the biggest users, has said the chip shortage comes amid rising demand for consumer electronics during the pandemic. "There's a serious imbalance in supply and demand of chips in the IT sector globally," the company's co-chief executive, Koh Dong-jin, said. Samsung has indicated it could delay the release of the next Galaxy Note smartphone until 2022 as a result of the shortage.

The US military needs to scale up its use of AI or be left behind by adversaries, Lt. Gen. Michael Groen, chief of the Pentagon's Joint AI Center (JAIC), told a recent conference of the National Defense Industrial Association, according to a report from UPI. While current military use of AI "is a step in the right direction, we need to start building on it," stated Groen, who was appointed head of the JAIC in October. He is the second director of JAIC, or "the jake" in Pentagon parlance, which was set up by Congress in 2018. The first director was Air Force Lt. Gen. John N.T. "Jack" Shanahan, who retired last year. Noting that China has said it intends "to be dominant in AI by 2030," the Pentagon has focused on a five-year program culminating in 2027.

This paper proposes a novel nature-inspired meta-heuristic algorithm called the Golden Tortoise Beetle Optimizer (GTBO) to solve optimization problems. It mimics golden tortoise beetle's behavior of changing colors to attract opposite sex for mating and its protective strategy that uses a kind of anal fork to deter predators. The algorithm is modeled based on the beetle's dual attractiveness and survival strategy to generate new solutions for optimization problems. To measure its performance, the proposed GTBO is compared with five other nature-inspired evolutionary algorithms on 24 well-known benchmark functions investigating the trade-off between exploration and exploitation, local optima avoidance, and convergence towards the global optima is statistically significant. We particularly applied GTBO to two well-known engineering problems including the welded beam design problem and the gear train design problem. The results demonstrate that the new algorithm is more efficient than the five baseline algorithms for both problems. A sensitivity analysis is also performed to reveal different impacts of the algorithm's key control parameters and operators on GTBO's performance.

Identification and categorization of social media posts generated during disasters are crucial to reduce the sufferings of the affected people. However, lack of labeled data is a significant bottleneck in learning an effective categorization system for a disaster. This motivates us to study the problem as unsupervised domain adaptation (UDA) between a previous disaster with labeled data (source) and a current disaster (target). However, if the amount of labeled data available is limited, it restricts the learning capabilities of the model. To handle this challenge, we utilize limited labeled data along with abundantly available unlabeled data, generated during a source disaster to propose a novel two-part graph neural network. The first-part extracts domain-agnostic global information by constructing a token level graph across domains and the second-part preserves local instance-level semantics. In our experiments, we show that the proposed method outperforms state-of-the-art techniques by $2.74\%$ weighted F$_1$ score on average on two standard public dataset in the area of disaster management. We also report experimental results for granular actionable multi-label classification datasets in disaster domain for the first time, on which we outperform BERT by $3.00\%$ on average w.r.t weighted F$_1$. Additionally, we show that our approach can retain performance when very limited labeled data is available.

Deployed into an open world, object detectors are prone to a type of false positive detection termed open-set errors. We propose GMM-Det, a real-time method for extracting epistemic uncertainty from object detectors to identify and reject open-set errors. GMM-Det trains the detector to produce a structured logit space that is modelled with class-specific Gaussian Mixture Models. At test time, open-set errors are identified by their low log-probability under all Gaussian Mixture Models. We test two common detector architectures, Faster R-CNN and RetinaNet, across three varied datasets spanning robotics and computer vision. Our results show that GMM-Det consistently outperforms existing uncertainty techniques for identifying and rejecting open-set detections, especially at the low-error-rate operating point required for safety-critical applications. GMM-Det maintains object detection performance, and introduces only minimal computational overhead. We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to consistently evaluate open-set performance in object detection. Code for GMM-Det and the dataset methodology will be made publicly available.

Sex robots could be hijacked by hackers and used to cause harm or even kill people, a cybersecurity expert has warned. Artificial intelligence researchers have consistently warned of the security risks posed by internet-connected robots, with hundreds recently calling on governments to ban weaponized robots. The latest warning comes from a cybersecurity expert who made the prophecy to several U.K. newspapers. "Hackers can hack into a robot or a robotic device and have full control of the connections, arms, legs and other attached tools like in some cases knives or welding devices," Nicholas Patterson, a cybersecurity lecturer at Deakin University in Melbourne, Australia, told the Star. "Often these robots can be upwards of 200 pounds and very strong. Once a robot is hacked, the hacker has full control and can issue instructions to the robot. The last thing you want is for a hacker to have control over one of these robots. Once hacked they could absolutely be used to perform physical actions for an advantageous scenario or to cause damage."

Since 2012, in a case-study in Bucaramanga-Colombia, 179 pedestrians died in car accidents, and another 2873 pedestrians were injured. Each day, at least one passerby is involved in a tragedy. Knowing the causes to decrease accidents is crucial, and using system-dynamics to reproduce the collisions' events is critical to prevent further accidents. This work implements simulations to save lives by reducing the city's accidental rate and suggesting new safety policies to implement. Simulation's inputs are video recordings in some areas of the city. Deep Learning analysis of the images results in the segmentation of the different objects in the scene, and an interaction model identifies the primary reasons which prevail in the pedestrians or vehicles' behaviours. The first and most efficient safety policy to implement - validated by our simulations - would be to build speed bumps in specific places before the crossings reducing the accident rate by 80%.

Plot-based Graphic API recommendation (Plot2API) is an unstudied but meaningful issue, which has several important applications in the context of software engineering and data visualization, such as the plotting guidance of the beginner, graphic API correlation analysis, and code conversion for plotting. Plot2API is a very challenging task, since each plot is often associated with multiple APIs and the appearances of the graphics drawn by the same API can be extremely varied due to the different settings of the parameters. Additionally, the samples of different APIs also suffer from extremely imbalanced. Considering the lack of technologies in Plot2API, we present a novel deep multi-task learning approach named Semantic Parsing Guided Neural Network (SPGNN) which translates the Plot2API issue as a multi-label image classification and an image semantic parsing tasks for the solution. In SPGNN, the recently advanced Convolutional Neural Network (CNN) named EfficientNet is employed as the backbone network for API recommendation. Meanwhile, a semantic parsing module is complemented to exploit the semantic relevant visual information in feature learning and eliminate the appearance-relevant visual information which may confuse the visual-information-based API recommendation. Moreover, the recent data augmentation technique named random erasing is also applied for alleviating the imbalance of API categories. We collect plots with the graphic APIs used to drawn them from Stack Overflow, and release three new Plot2API datasets corresponding to the graphic APIs of R and Python programming languages for evaluating the effectiveness of Plot2API techniques. Extensive experimental results not only demonstrate the superiority of our method over the recent deep learning baselines but also show the practicability of our method in the recommendation of graphic APIs.

Context: Previous studies have shown that training data instance selection based on nearest neighborhood (NN) information can lead to better performance in cross project defect prediction (CPDP) by reducing heterogeneity in training datasets. However, neighborhood calculation is computationally expensive and approximate methods such as Locality Sensitive Hashing (LSH) can be as effective as exact methods. Aim: We aim at comparing instance selection methods for CPDP, namely LSH, NN-filter, and Genetic Instance Selection (GIS). Method: We conduct experiments with five base learners, optimizing their hyper parameters, on 13 datasets from PROMISE repository in order to compare the performance of LSH with benchmark instance selection methods NN-Filter and GIS. Results: The statistical tests show six distinct groups for F-measure performance. The top two group contains only LSH and GIS benchmarks whereas the bottom two groups contain only NN-Filter variants. LSH and GIS favor recall more than precision. In fact, for precision performance only three significantly distinct groups are detected by the tests where the top group is comprised of NN-Filter variants only. Recall wise, 16 different groups are identified where the top three groups contain only LSH methods, four of the next six are GIS only and the bottom five contain only NN-Filter. Finally, NN-Filter benchmarks never outperform the LSH counterparts with the same base learner, tuned or non-tuned. Further, they never even belong to the same rank group, meaning that LSH is always significantly better than NN-Filter with the same learner and settings. Conclusions: The increase in performance and the decrease in computational overhead and runtime make LSH a promising approach. However, the performance of LSH is based on high recall and in environments where precision is considered more important NN-Filter should be considered.