Background and aim: Image registration and alignment are the main limitations of augmented reality-based knee replacement surgery. This research aims to decrease the registration error, eliminate outcomes that are trapped in local minima to improve the alignment problems, handle the occlusion, and maximize the overlapping parts. Methodology: markerless image registration method was used for Augmented reality-based knee replacement surgery to guide and visualize the surgical operation. While weight least square algorithm was used to enhance stereo camera-based tracking by filling border occlusion in right to left direction and non-border occlusion from left to right direction. Results: This study has improved video precision to 0.57 mm~0.61 mm alignment error. Furthermore, with the use of bidirectional points, for example, forwards and backwards directional cloud point, the iteration on image registration was decreased. This has led to improve the processing time as well. The processing time of video frames was improved to 7.4~11.74 fps. Conclusions: It seems clear that this proposed system has focused on overcoming the misalignment difficulty caused by movement of patient and enhancing the AR visualization during knee replacement surgery. The proposed system was reliable and favorable which helps in eliminating alignment error by ascertaining the optimal rigid transformation between two cloud points and removing the outliers and non-Gaussian noise. The proposed augmented reality system helps in accurate visualization and navigation of anatomy of knee such as femur, tibia, cartilage, blood vessels, etc.

Abstract--Machine learning (ML) models are constructed by expert ML practitioners using various coding languages, in which they tune and select models hyperparameters and learning algorithms for a given problem domain. They also carefully design an objective function or loss function (often with multiple objectives) that captures the desired output for a given ML task such as classification, regression, etc. In multi-objective optimization, conflicting objectives and constraints is a major area of concern. In such problems, several competing objectives are seen for which no single optimal solution is found that satisfies all desired objectives simultaneously. In the past VA systems have allowed users to interactively construct objective functions for a classifier. In this paper, we extend this line of work by prototyping a technique to visualize multi-objective objective functions either defined in a Jupyter notebook or defined using an interactive visual interface to help users to: (1) perceive and interpret complex mathematical terms in it and (2) detect and resolve conflicting objectives. Visualization of the objective function enlightens potentially conflicting objectives that obstructs selecting correct solution(s) for the desired ML task or goal. We also present an enumeration of potential conflicts in objective specification in multi-objective objective functions for classifier selection. Furthermore, we demonstrate our approach in a VA system that helps users in specifying meaningful objective functions to a classifier by detecting and resolving conflicting objectives and constraints. Through a within-subject quantitative and qualitative user study, we present results showing that our technique helps users interactively specify meaningful objective functions by resolving potential conflicts for a classification task. In the past, researchers in visual analytics (VA) have investigated making ML model construction interactive, which means developing visual interfaces that allow users to construct ML models by interacting with graphical widgets or data marks [1], [2]. For example, the system XClusim helps biologists to interactively cluster a specified dataset [3], Hypermoval [4] and BEAMES [5] allows interactive construction of regression models, Axissketcher allows dimension reduction using simple drag-drop interactions [6]. Workflow adopted in the system CACTUS. Recently, Das et al. have demonstrated that may result into incorrectly predicting many relevant data a VA system, QUESTO [7] that facilitated interactive creation of instances, though improving the generalizability of the model. Here objective functions to solve a classification task utilising an Auto-the objective to train a model with high accuracy on a set of ML system.

We introduce an approach to recommending short-lived dynamic packages for golf booking services. Two challenges are addressed in this work. The first is the short life of the items, which puts the system in a state of a permanent cold start. The second is the uninformative nature of the package attributes, which makes clustering or figuring latent packages challenging. Although such settings are fairly pervasive, they have not been studied in traditional recommendation research, and there is thus a call for original approaches for recommender systems. In this paper, we introduce a hybrid method that leverages user analysis and its relation to the packages, as well as package pricing and environmental analysis, and traditional collaborative filtering. The proposed approach achieved appreciable improvement in precision compared with baselines.

We recently mentioned the autonomous video-interviewing system that appeared to be grading candidates on the strength of the bookcase behind them (27 February). Now a paper published on the website of the company OpenAI reveals how CLIP, a neural network system that learns to recognise visual concepts through being fed verbal descriptions of them, can be spoofed simply by overlaying an image with text declaring it to be something else. Stick a sticker on an apple declaring it to be a different apple product, an iPod, and the AI says it is an iPod 99.7 per cent of the time. Plaster dollar signs on a picture of anything, from a poodle to a chainsaw to a horse chestnut, and, with a charmingly artless naivety, CLIP mostly returns the answer "piggy bank". This suggests an excellent way to defy privacy-violating face-recognition systems when on nefarious business: simply attach a sheet of paper about your person declaring yourself to be your favourite frenemy or privacy violating tech guru.

If you've ever wanted to know what it might be like to see Kim Jong-un let loose at karaoke, your wish has been granted, thanks to an app that lets users turn photographs of anyone – or anything remotely resembling a face – into uncanny AI-powered videos of them lip syncing famous songs. The app is called Wombo AI, and while the future of artificial intelligence and the ability to make fake videos of real people strikes fear into the hearts of many experts, some say that Wombo could help by raising awareness of "deepfakes". Wombo CEO Ben-Zion Benkhin said he came up with the idea "while smoking a joint with my roommate on the roof". The app launched in Canada in February and has since been downloaded on Apple's App store and Google Play more than 2m times. There are 15 songs users can choose from, including Michael Jackson's Thriller and the more recent Gunther's Ding Dong Song.

We propose a complexity measure of a neural network mapping function based on the diversity of the set of tangent spaces from different inputs. Treating each tangent space as a linear PAC concept we use an entropy-based measure of the bundle of concepts in order to estimate the conceptual capacity of the network. The theoretical maximal capacity of a ReLU network is equivalent to the number of its neurons. In practice however, due to correlations between neuron activities within the network, the actual capacity can be remarkably small, even for very big networks. Empirical evaluations show that this new measure is correlated with the complexity of the mapping function and thus the generalisation capabilities of the corresponding network. It captures the effective, as oppose to the theoretical, complexity of the network function. We also showcase some uses of the proposed measure for analysis and comparison of trained neural network models.

Real world datasets are heavily skewed where some classes are significantly outnumbered by the other classes. In these situations, machine learning algorithms fail to achieve substantial efficacy while predicting these under-represented instances. To solve this problem, many variations of synthetic minority over-sampling methods (SMOTE) have been proposed to balance the dataset which deals with continuous features. However, for datasets with both nominal and continuous features, SMOTE-NC is the only SMOTE-based over-sampling technique to balance the data. In this paper, we present a novel minority over-sampling method, SMOTE-ENC (SMOTE - Encoded Nominal and Continuous), in which, nominal features are encoded as numeric values and the difference between two such numeric value reflects the amount of change of association with minority class. Our experiments show that the classification model using SMOTE-ENC method offers better prediction than model using SMOTE-NC when the dataset has a substantial number of nominal features and also when there is some association between the categorical features and the target class. Additionally, our proposed method addressed one of the major limitations of SMOTE-NC algorithm. SMOTE-NC can be applied only on mixed datasets that have features consisting of both continuous and nominal features and cannot function if all the features of the dataset are nominal. Our novel method has been generalized to be applied on both mixed datasets and on nominal only datasets. The code is available from mkhushi.github.io

Why do models often attend to salient words, and how does this evolve throughout training? We approximate model training as a two stage process: early on in training when the attention weights are uniform, the model learns to translate individual input word `i` to `o` if they co-occur frequently. Later, the model learns to attend to `i` while the correct output is $o$ because it knows `i` translates to `o`. To formalize, we define a model property, Knowledge to Translate Individual Words (KTIW) (e.g. knowing that `i` translates to `o`), and claim that it drives the learning of the attention. This claim is supported by the fact that before the attention mechanism is learned, KTIW can be learned from word co-occurrence statistics, but not the other way around. Particularly, we can construct a training distribution that makes KTIW hard to learn, the learning of the attention fails, and the model cannot even learn the simple task of copying the input words to the output. Our approximation explains why models sometimes attend to salient words, and inspires a toy example where a multi-head attention model can overcome the above hard training distribution by improving learning dynamics rather than expressiveness.

Abstract-- The General Data Protection Regulation (GDPR) aims to ensure that all personal data processing activities are fair and transparent for the European Union (EU) citizens, regardless of whether these are carried out within the EU or anywhere else. To this end, it sets strict requirements to transfer personal data outside the EU. However, checking these requirements is a daunting task for supervisory authorities, particularly in the mobile app domain due to the huge number of apps available and their dynamic nature. In this paper, we propose a fully automated method to assess compliance of mobile apps with the GDPR requirements for cross-border personal data transfers. We have applied the method to the top-free 10,080 apps from the Google Play Store. The results reveal that there is still a very significant gap between what app providers and third-party recipients do in practice and what is intended by the GDPR. A substantial 56% of analysed apps are potentially non-compliant with the GDPR cross-border transfer requirements. THE distributed nature of today's digital systems and services across the world [1], or shared between chains of thirdparty not only facilitates the collection of personal data service providers [6], even without the app developer's from individuals anywhere, but also their transfer to different knowledge [7]. Second, apps are distributed through countries around the world [1]. This raises potential global stores, enabling app providers to easily reach markets risks to the privacy of individuals, as the organizations and users beyond its country of residence. In this sending and receiving personal data can be subject to different context, there is a need for constant vigilance by the various data protection laws and, therefore, may not offer an stakeholders, including app developers, supervisory equivalent level of protection.

Deep Convolutional Neural Network (DCNN) and Transformer have achieved remarkable successes in image recognition. However, their performance in fine-grained image recognition is still difficult to meet the requirements of actual needs. This paper proposes a Sequence Random Network (SRN) to enhance the performance of DCNN. The output of DCNN is one-dimensional features. This one-dimensional feature abstractly represents image information, but it does not express well the detailed information of image. To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image. After the feature transform by BiLSTM-TDN, the recognition performance has been greatly improved. We conducted the experiments on six fine-grained image datasets. Except for FGVC-Aircraft, the accuracies of the proposed methods on the other datasets exceeded 99%. Experimental results show that BiLSTM-TDN is far superior to the existing state-of-the-art methods. In addition to DCNN, BiLSTM-TDN can also be extended to other models, such as Transformer.