Deep learning (DL) has been increasingly adopted by a variety of software-intensive systems.

Are you excited to enter the Data Science world? That's still the right choice because of the ultimate boost in need of work done in Data Science and Artificial Intelligence during this pandemic. Although, because of the crisis, the market currently gets tougher to be able to set it up again with more men force as they are doing earlier. So, It might possible that you have to prepare yourself mentally for the long run hiring journey and many rejections in along the way. Hereby, while writing this article, I am assuming that you already know that a data science portfolio is crucial and how to build it up.

The headline that appeared in this opinion page on Tuesday was striking, "A robot wrote this entire article. Are you scared yet, human?" The claim was disconcerting for many, perhaps most of all for those of us who write op-eds for a living. We felt the alarm of countless knowledge economy workers who toil beneath a computerized sword of Damocles, fearful that our entire career might be replaced in the (not so distant) future by new forms of artificial intelligence. But while the anxiety of economic displacement is quite real, the danger is largely a phantom … at least for now.

In the recent past, there has been a growing interest in Neural-Symbolic Integration frameworks, i.e., hybrid systems that integrate connectionist and symbolic approaches: on the one hand, neural networks show remarkable abilities to learn from a large amount of data in presence of noise, on the other, pure symbolic methods can perform reasoning as well as learning from few samples. By combining the two paradigms, it should be possible to obtain a system that can both learn from data and apply inference over some background knowledge. Here we propose KENN (Knowledge Enhanced Neural Networks), a Neural-Symbolic architecture that injects prior knowledge, codified in a set of universally quantified FOL clauses, into a neural network model. In KENN, clauses are used to generate a new final layer of the neural network which modifies the initial predictions based on the knowledge. Among the advantages of this strategy, there is the possibility to include additional learnable parameters, the clause weights, each of which represents the strength of a specific clause. We evaluated KENN on two standard datasets for multi-label classification, showing that the injection of clauses, automatically extracted from the training data, sensibly improves the performances. In a further experiment with manually curated knowledge, KENN outperformed state-of-the-art methods on the VRD Dataset, where the task is to classify relationships between detected objects in images. Finally, to evaluate how KENN deals with relational data, we tested it with different learning configurations on Citeseer, a standard dataset for Collective Classification. The obtained results show that KENN is capable of increasing the performances of the underlying neural network even in the presence of relational data obtaining results in line with other methods that combine learning with logic.

In the field of medical imaging, chest radiographs, or X-rays remain as the gold standard for interpreting lung conditions of one and play an important role in clinical care treatment. Recent years witnessed the rising remarkable success of Artificial intelligence (AI) technology in various fields such as computer vision or health services. In detection of diseases in medical images, especially in radiographs, AIbased systems have proven to be powerful tools that can handle medical challenges quickly and cheaply and thereby can significantly improve diagnostics quality and ultimately treat the disease. For examples, detection of skin cancers has been enabled by a vast number of accurate deep learning studies in 2019 such as [1] [2] or [3]. Mammography, which is usually used to detect breast cancer has been the interest of such deep learning studies [4] [5]. A recent advanced study has also been conducted on the use of deep learning to identify Appendicitis using videos that contain CT scans[6]. For radiographs, scientists also applied deep learning to detect particular conditions of lung health, such as pneumonia or consolidation, etc.... Merely, Deep Learning has proven its efficiency in a recent study to generate new synthesis data for training [7]. Some works even lead to the conclusion that AIbased systems can suppress the performance of normal medical doctors or qualified experts in diseases detection [8] [9].

As a pre-trained Transformer model, BERT (Bidirectional Encoder Representations from Transformers) has achieved ground-breaking performance on multiple NLP tasks. On the other hand, Boosting is a popular ensemble learning technique which combines many base classifiers and has been demonstrated to yield better generalization performance in many machine learning tasks. Some works have indicated that ensemble of BERT can further improve the application performance. However, current ensemble approaches focus on bagging or stacking and there has not been much effort on exploring the boosting. In this work, we proposed a novel Boosting BERT model to integrate multi-class boosting into the BERT. Our proposed model uses the pre-trained Transformer as the base classifier to choose harder training sets to fine-tune and gains the benefits of both the pre-training language knowledge and boosting ensemble in NLP tasks. We evaluate the proposed model on the GLUE dataset and 3 popular Chinese NLU benchmarks. Experimental results demonstrate that our proposed model significantly outperforms BERT on all datasets and proves its effectiveness in many NLP tasks. Replacing the BERT base with RoBERTa as base classifier, BoostingBERT achieves new state-of-the-art results in several NLP Tasks. We also use knowledge distillation within the "teacher-student" framework to reduce the computational overhead and model storage of BoostingBERT while keeping its performance for practical application.

Safety concerns on the deep neural networks (DNNs) have been raised when they are applied to critical sectors. In this paper, we define safety risks by requesting the alignment of the network's decision with human perception. To enable a general methodology for quantifying safety risks, we define a generic safety property and instantiate it to express various safety risks. For the quantification of risks, we take the maximum radius of safe norm balls, in which no safety risk exists. The computation of the maximum safe radius is reduced to the computation of their respective Lipschitz metrics - the quantities to be computed. In addition to the known adversarial example, reachability example, and invariant example, in this paper we identify a new class of risk - uncertainty example - on which humans can tell easily but the network is unsure. We develop an algorithm, inspired by derivative-free optimization techniques and accelerated by tensor-based parallelization on GPUs, to support efficient computation of the metrics. We perform evaluations on several benchmark neural networks, including ACSC-Xu, MNIST, CIFAR-10, and ImageNet networks. The experiments show that, our method can achieve competitive performance on safety quantification in terms of the tightness and the efficiency of computation. Importantly, as a generic approach, our method can work with a broad class of safety risks and without restrictions on the structure of neural networks.

It has become increasingly challenging to distinguish real faces from their visually realistic fake counterparts, due to the great advances of deep learning based face manipulation techniques in recent years. In this paper, we introduce a deep learning method to detect face manipulation. It consists of two stages: feature extraction and binary classification. To better distinguish fake faces from real faces, we resort to the triplet loss function in the first stage. We then design a simple linear classification network to bridge the learned contrastive features with the real/fake faces. Experimental results on public benchmark datasets demonstrate the effectiveness of this method, and show that it generates better performance than state-of-the-art techniques in most cases.

Skin cancer is by far in top-3 of the world's most common cancer. Among different skin cancer types, melanoma is particularly dangerous because of its ability to metastasize. Early detection is the key to success in skin cancer treatment. However, skin cancer diagnosis is still a challenge, even for experienced dermatologists, due to strong resemblances between benign and malignant lesions. To aid dermatologists in skin cancer diagnosis, we developed a deep learning system that can effectively and automatically classify skin lesions into one of the seven classes: (1) Actinic Keratoses, (2) Basal Cell Carcinoma, (3) Benign Keratosis, (4) Dermatofibroma, (5) Melanocytic nevi, (6) Melanoma, (7) Vascular Skin Lesion. The HAM10000 dataset was used to train the system. An end-to-end deep learning process, transfer learning technique, utilizing multiple pre-trained models, combining with class-weighted and focal loss were applied for the classification process. The result was that our ensemble of modified ResNet50 models can classify skin lesions into one of the seven classes with top-1, top-2 and top-3 accuracy 93%, 97% and 99%, respectively. This deep learning system can potentially be integrated into computer-aided diagnosis systems that support dermatologists in skin cancer diagnosis.

With the rapid development in online education, knowledge tracing (KT) has become a fundamental problem which traces students' knowledge status and predicts their performance on new questions. Questions are often numerous in online education systems, and are always associated with much fewer skills. However, the previous literature fails to involve question information together with high-order question-skill correlations, which is mostly limited by data sparsity and multi-skill problems. From the model perspective, previous models can hardly capture the long-term dependency of student exercise history, and cannot model the interactions between student-questions, and student-skills in a consistent way. In this paper, we propose a Graph-based Interaction model for Knowledge Tracing (GIKT) to tackle the above probems. More specifically, GIKT utilizes graph convolutional network (GCN) to substantially incorporate question-skill correlations via embedding propagation. Besides, considering that relevant questions are usually scattered throughout the exercise history, and that question and skill are just different instantiations of knowledge, GIKT generalizes the degree of students' master of the question to the interactions between the student's current state, the student's history related exercises, the target question, and related skills. Experiments on three datasets demonstrate that GIKT achieves the new state-of-the-art performance, with at least 1% absolute AUC improvement.