Computer vision technology is increasingly used in areas such as automatic surveillance systems, self-driving cars, facial recognition, healthcare and social distancing tools. Users require accurate and reliable visual information to fully harness the benefits of video analytics applications but the quality of the video data is often affected by environmental factors such as rain, night-time conditions or crowds (where there are multiple images of people overlapping with each other in a scene). Using computer vision and deep learning, a team of researchers led by Yale-NUS College Associate Professor of Science (Computer Science) Robby Tan, who is also from the National University of Singapore's (NUS) Faculty of Engineering, has developed novel approaches that resolve the problem of low-level vision in videos caused by rain and night-time conditions, as well as improve the accuracy of 3D human pose estimation in videos. The research was presented at the 2021 Conference on Computer Vision and Pattern Recognition (CVPR), a top ranked computer science conference. Night-time images are affected by low light and man-made light effects such as glare, glow, and floodlights, while rain images are affected by rain streaks or rain accumulation (or rain veiling effect).

A large portion of feeling more fulfilled in your career is from the feeling of progress. For a while, that feeling has been void for me. Yes, I've still been landing freelance machine learning contracts but not exactly the ones I want -- with all due respect to my current clients. While I'm grateful for the opportunities I've been receiving, I know that I must improve if I want to reach the goals I've set for my career. I didn't become a Freelancer to do work I don't want to do.

Artificial Intelligence is creating cutting-edge technologies for more efficient workflow in multiple industries across the world in this tech-driven era. There are machine learning and deep learning algorithms that are too complicated for people to understand besides AI engineers or related employees. Artificial Intelligence has generated self-explaining algorithms for stakeholders and partners to comprehend the entire process of transforming enormous complex sets of real-time data into meaningful in-depth insights. This is known as Explainable Artificial Intelligence or XAI in which the results of these solutions can be easily understood by humans. It helps AI designers to explain how AI machines have generated a specific kind of insight or outcome for businesses to thrive in the market. Multiple online courses and platforms are available for a better understanding of Explainable AI by designing interpretable and inclusive Artificial Intelligence.

Computer vision has progressed much over the past decade and made its way into all sorts of relevant applications, both in academia and in our daily lives. There are, however, some tasks in this field that are still extremely difficult for computers to perform with acceptable accuracy and speed. One example is object tracking, which involves recognizing persistent objects in video footage and tracking their movements. While computers can simultaneously track more objects than humans, they usually fail to discriminate the appearance of different objects. This, in turn, can lead to the algorithm to mix up objects in a scene and ultimately produce incorrect tracking results.

Backpropagation (BP) is a core component of the contemporary deep learning incarnation of neural networks. Briefly, BP is an algorithm that exploits the computational architecture of neural networks to efficiently evaluate the gradient of a cost function during neural network parameter optimization. The validity of BP rests on the application of a multivariate chain rule to the computational architecture of neural networks and their associated objective functions. Introductions to deep learning theory commonly present the computational architecture of neural networks in matrix form, but eschew a parallel formulation and justification of BP in the framework of matrix differential calculus. This entails several drawbacks for the theory and didactics of deep learning. In this work, we overcome these limitations by providing a full induction proof of the BP algorithm in matrix notation. Specifically, we situate the BP algorithm in the framework of matrix differential calculus, encompass affine-linear potential functions, prove the validity of the BP algorithm in inductive form, and exemplify the implementation of the matrix form BP algorithm in computer code.

Although virtual agents are increasingly situated in environments where natural language is the most effective mode of interaction with humans, these exchanges are rarely used as an opportunity for learning. Leveraging language interactions effectively requires addressing limitations in the two most common approaches to language grounding: semantic parsers built on top of fixed object categories are precise but inflexible and end-to-end models are maximally expressive, but fickle and opaque. Our goal is to develop a system that balances the strengths of each approach so that users can teach agents new instructions that generalize broadly from a single example. We introduce the idea of neural abstructions: a set of constraints on the inference procedure of a label-conditioned generative model that can affect the meaning of the label in context. Starting from a core programming language that operates over abstructions, users can define increasingly complex mappings from natural language to actions. We show that with this method a user population is able to build a semantic parser for an open-ended house modification task in Minecraft. The semantic parser that results is both flexible and expressive: the percentage of utterances sourced from redefinitions increases steadily over the course of 191 total exchanges, achieving a final value of 28%.

Deep learning based visual to sound generation systems essentially need to be developed particularly considering the synchronicity aspects of visual and audio features with time. In this research we introduce a novel task of guiding a class conditioned generative adversarial network with the temporal visual information of a video input for visual to sound generation task adapting the synchronicity traits between audio-visual modalities. Our proposed FoleyGAN model is capable of conditioning action sequences of visual events leading towards generating visually aligned realistic sound tracks. We expand our previously proposed Automatic Foley dataset to train with FoleyGAN and evaluate our synthesized sound through human survey that shows noteworthy (on average 81\%) audio-visual synchronicity performance. Our approach also outperforms in statistical experiments compared with other baseline models and audio-visual datasets.

Biosemiosis is a process of choice-making between simultaneously alternative options. It is well-known that, when sufficiently young children encounter a new word, they tend to interpret it as pointing to a meaning that does not have a word yet in their lexicon rather than to a meaning that already has a word attached. In previous research, the strategy was shown to be optimal from an information theoretic standpoint. In that framework, interpretation is hypothesized to be driven by the minimization of a cost function: the option of least communication cost is chosen. However, the information theoretic model employed in that research neither explains the weakening of that vocabulary learning bias in older children or polylinguals nor reproduces Zipf's meaning-frequency law, namely the non-linear relationship between the number of meanings of a word and its frequency. Here we consider a generalization of the model that is channeled to reproduce that law. The analysis of the new model reveals regions of the phase space where the bias disappears consistently with the weakening or loss of the bias in older children or polylinguals. The model is abstract enough to support future research on other levels of life that are relevant to biosemiotics. In the deep learning era, the model is a transparent low-dimensional tool for future experimental research and illustrates the predictive power of a theoretical framework originally designed to shed light on the origins of Zipf's rank-frequency law.

Quantum computing has gained a lot of attention in recent years due to its potential to solve complex problems which would take exponential time in classical computers. Most of the research efforts have been focused on constructing quantum computers based on qubits [1]. However, there has been a growing interest in building quantum computers based on qudits, i.e. machines that simulate and operate d-dimensional quantum states, with d > 2. Various physical implementations of high-dimensional quantum states have been proposed, such as photonic states integrated in chips [2, 3], photonic modes encoded in the orbital angular momentum (OAM) [4], ion traps [5], ququarts implemented on a quadrupolar nuclear magnetic resonance (NMR) [6], and molecular quantum magnets [7]. Two of the main advantages of highdimensional quantum computers compared to their qubit-based counterparts are their larger information storage [8], and their higher resilience to noise [9]. One closely related field of quantum computing is quantum machine learning (QML). This field aims to develop novel quantum-inspired machine learning (ML) methods that may run on classical or quantum computers and to implement the existing ML algorithms on quantum computers. For instance, some classical machine learning algorithms like support vector machines and restricted Boltzmann machines can be implemented on qubit-based quantum computers [10, 11], and many of the ML methods have been reformulated in the language of quantum physics like quantum decision trees [12], quantum neural networks [13, 14], and quantum generative adversarial networks [15]. In contrast with QML methods built on qubits, less research has been done on QML based on qudits, i.e. algorithms that run in high-dimensional quantum computers. Some of these methods include protocols with qudits for reinforcement learning [16], and for training quantum neural networks [17, 18, 19].

Electromyogram (EMG) has been utilized to interface signals for prosthetic hands and information devices owing to its ability to reflect human motion intentions. Although various EMG classification methods have been introduced into EMG-based control systems, they do not fully consider the stochastic characteristics of EMG signals. This paper proposes an EMG pattern classification method incorporating a scale mixture-based generative model. A scale mixture model is a stochastic EMG model in which the EMG variance is considered as a random variable, enabling the representation of uncertainty in the variance. This model is extended in this study and utilized for EMG pattern classification. The proposed method is trained by variational Bayesian learning, thereby allowing the automatic determination of the model complexity. Furthermore, to optimize the hyperparameters of the proposed method with a partial discriminative approach, a mutual information-based determination method is introduced. Simulation and EMG analysis experiments demonstrated the relationship between the hyperparameters and classification accuracy of the proposed method as well as the validity of the proposed method. The comparison using public EMG datasets revealed that the proposed method outperformed the various conventional classifiers. These results indicated the validity of the proposed method and its applicability to EMG-based control systems. In EMG pattern recognition, a classifier based on a generative model that reflects the stochastic characteristics of EMG signals can outperform the conventional general-purpose classifier.