… from coding to artificial intelligence, machine learning and deep learning, said Dr Raja M, head of the campus’ Department of Computer Science.

Deep learning is a type of machine learning in which a model learns to perform classification tasks directly from images, text or sound. Image-based deep learning models (DLMs) have been used in other disciplines, but this method has yet to be used to predict surgical outcomes. With this background, researchers carried out a study to examine whether deep learning models (DLMs) using routine preoperative imaging can predict surgical complexity and outcomes in abdominal wall reconstruction. They applied image-based deep learning to predict complexity, defined as need for component separation, and pulmonary and wound complications after abdominal wall reconstruction (AWR). This quality improvement study was performed at an 874-bed hospital and tertiary hernia referral center from September 2019 to January 2020.

In the technology world, where the buzzwords are now shifting from software development to data science and especially Machine Learning and Deep Learning, it becomes important for young data science aspirants to know the real difference between these two technologies. Let's start with Machine Learning.

In all, a few lines of R or Python code will suffice for a piece of machine intelligence and there's a plethora of resources and tutorials online to train your quasi-neural networks, like all sorts of deepfake networks, manipulating image-video-audio-text, with zero knowledge of the world, as Generative Adversarial Networks, BigGAN, CycleGAN, StyleGAN, GauGAN, Artbreeder, DeOldify, etc. They create and modify faces, landscapes, universal images, etc., with zero understanding what it is all about.

Hope you had a great week. We have a new leader on the SuperGLUE benchmark with a new Ernie model from Baidu comprising of 10 billion parameters trained on on a 4TB corpus. FYI, human baseline was already beat by Microsoft's DeBERTa model at the beginning of the year… time for a new SuperSuperGLUE benchmark??? BTW, if you are still interested in GitHub's CoPilot, I stumbled upon the Codex paper this week: DeepMind's Perceiver transformer allows it to take a variety of modalities (vision, audio, text) as its input and able to achieve competitive outcomes in benchmark performance. Usually a model architecture is specialized to a specific domain, however what the Perceiver is attempting to do here is being able to generalize to any domain using a single architecture. Adding to the list of efficient transformers, comes the LS-Transformer that be both used for autoregressive and bi-directional models and for both language and vision domains.

Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this paper, a novel method by acting the gradient activation function (GAF) on the gradient is proposed to handle these challenges. Intuitively, the GAF enlarges the tiny gradients and restricts the large gradient. Theoretically, this paper gives conditions that the GAF needs to meet, and on this basis, proves that the GAF alleviates the problems mentioned above. In addition, this paper proves that the convergence rate of SGD with the GAF is faster than that without the GAF under some assumptions. Furthermore, experiments on CIFAR, ImageNet, and PASCAL visual object classes confirm the GAF's effectiveness. The experimental results also demonstrate that the proposed method is able to be adopted in various deep neural networks to improve their performance. The source code is publicly available at https://github.com/LongJin-lab/Activated-Gradients-for-Deep-Neural-Networks.

Probabilistic graphical models provide a powerful tool to describe complex statistical structure, with many real-world applications in science and engineering from controlling robotic arms to understanding neuronal computations. A major challenge for these graphical models is that inferences such as marginalization are intractable for general graphs. These inferences are often approximated by a distributed message-passing algorithm such as Belief Propagation, which does not always perform well on graphs with cycles, nor can it always be easily specified for complex continuous probability distributions. Such difficulties arise frequently in expressive graphical models that include intractable higher-order interactions. In this paper we construct iterative message-passing algorithms using Graph Neural Networks defined on factor graphs to achieve fast approximate inference on graphical models that involve many-variable interactions. Experimental results on several families of graphical models demonstrate the out-of-distribution generalization capability of our method to different sized graphs, and indicate the domain in which our method gains advantage over Belief Propagation.

Explainable Artificial Intelligence (XAI) is an emerging area of research in the field of Artificial Intelligence (AI). XAI can explain how AI obtained a particular solution (e.g., classification or object detection) and can also answer other "wh" questions. This explainability is not possible in traditional AI. Explainability is essential for critical applications, such as defense, health care, law and order, and autonomous driving vehicles, etc, where the know-how is required for trust and transparency. A number of XAI techniques so far have been purposed for such applications. This paper provides an overview of these techniques from a multimedia (i.e., text, image, audio, and video) point of view. The advantages and shortcomings of these techniques have been discussed, and pointers to some future directions have also been provided.

Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the information of the Chinese character structure after integrating the lexical information. Chinese characters have evolved from pictographs since ancient times, and their structure often reflects more information about the characters. This paper presents a novel Multi-metadata Embedding based Cross-Transformer (MECT) to improve the performance of Chinese NER by fusing the structural information of Chinese characters. Specifically, we use multi-metadata embedding in a two-stream Transformer to integrate Chinese character features with the radical-level embedding. With the structural characteristics of Chinese characters, MECT can better capture the semantic information of Chinese characters for NER. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits and superiority of the proposed MECT method.\footnote{The source code of the proposed method is publicly available at https://github.com/CoderMusou/MECT4CNER.

Storytelling is an open-ended task that entails creative thinking and requires a constant flow of ideas. Natural language generation (NLG) for storytelling is especially challenging because it requires the generated text to follow an overall theme while remaining creative and diverse to engage the reader. In this work, we introduce a system and a web-based demo, FairyTailor, for human-in-the-loop visual story co-creation. Users can create a cohesive children's fairytale by weaving generated texts and retrieved images with their input. FairyTailor adds another modality and modifies the text generation process to produce a coherent and creative sequence of text and images. To our knowledge, this is the first dynamic tool for multimodal story generation that allows interactive co-formation of both texts and images. It allows users to give feedback on co-created stories and share their results.