So, there are tons of content on neural networks but, rarely are these focused on the maths. Even if there is such content, it's so much complex that we just leave it. And I believe, without that deeper understanding of how maths is actually working, it's really difficult to get the proper intuition and it will always be a magical blackbox to us. This is my third blog in the series. In case you haven't checked my previous articles I would highly recommend to do so, since I'll building concepts on top of those.

We already covered in a previous post, how important it is to deal with uncertainty in financial Deep Learning forecasts. In this post, we'll attempt a first introduction on how we deal with explainability. Neural networks have been applied to various tasks including stock price prediction. Although highly successfully, these models are frequently treated as black boxes. In most cases we know that the performance on the test data is satisfying, but we do not know why the model came up with a specific output.

The problem of 3D object detection is of particular importance in robotic applications that require decision making or interactions with objects in the real world. While recently developed 2D detection algorithms are capable of handling large variations in viewpoint and clutter, accurate 3D object detection largely remains an open problem despite some promising recent work. They first regress relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. Given estimated orientation and dimensions and the constraint that the projection of the 3D bounding box fits tightly into the 2D detection window, they recover the translation and the object's 3D bounding box. In order to study this article mathematically, we need a coordinate system.

For a long time, I heard that the problem of time series could only be approached by statistical methods (AR[1], AM[2], ARMA[3], ARIMA[4]). These techniques are generally used by mathematicians who try to improve them continuously to constrain stationary and non-stationary time series. A friend of mine (mathematician, professor of statistics, and specialist in non-stationary time series) offered me several months ago to work on the validation and improvement of techniques to reconstruct the lightcurve of stars. Indeed, the Kepler satellite[11], like many other satellites, could not continuously measure the intensity of the luminous flux of nearby stars. The Kepler satellite was dedicated between 2009 and 2016 to search for planets outside our Solar System called extrasolar planets or exoplanets. As you have understood, we are going to travel a little further than our planet Earth and deep dive into a galactic journey whose machine learning will be our vessel.

Verdict lists ten of the most popular tweets on artificial intelligence (AI) in August 2020 based on data from GlobalData's Influencer Platform. The top tweets were chosen from influencers as tracked by GlobalData's Influencer Platform, which is based on a scientific process that works on pre-defined parameters. Influencers are selected after a deep analysis of the influencer's relevance, network strength, engagement, and leading discussions on new and emerging trends. Ronald van Loon, principal analyst and CEO of Intelligent World, shared a video from the World Economic Forum on a neural machine translation technology developed by Google to provide natural translation between different languages using artificial intelligence and deep learning. The system was also used to translate two languages without using English as a bridge.

We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an image-based deep neural network model is trained to produce small and realistic modifications to an original image in order to cause user-defined effects. These modifications can be used in the design process of image-based robust control - to determine the ability of the controller to return to a working regime by modifications in the input space, rather than by adaptation. In contrast to conventional control design approaches, where robustness is quantified in terms of the ability to reject noise, we explore the space of counterfactuals that might cause a certain requirement to be violated, thus proposing an alternative model that might be more expressive in certain robotics applications. So, we propose the generation of counterfactuals as an approach to explanation of black-box models and the envisioning of potential movement paths in autonomous robotic control. Firstly, we demonstrate this approach in a set of classification tasks, using the well known MNIST and CelebFaces Attributes datasets. Then, addressing multi-dimensional regression, we demonstrate our approach in a reaching task with a physical robot, and in a navigation task with a robot in a digital twin simulation.

Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance comparison to previous work. In this paper, we first identify several patterns of invalid comparisons in published papers and describe them to avoid their propagation. We then propose a small empirical study to quantify the impact of the most common mistake and evaluate it leads to overestimating the final RE performance by around 5% on ACE05. We also seize this opportunity to study the unexplored ablations of two recent developments: the use of language model pretraining (specifically BERT) and span-level NER. This meta-analysis emphasizes the need for rigor in the report of both the evaluation setting and the datasets statistics and we call for unifying the evaluation setting in end-to-end RE.

Lately there has been a lot of discussion about why deep learning algorithms perform better than we would theoretically suspect. To get insight into this question, it helps to improve our understanding of how learning works. We explore the core problem of generalization and show that long-accepted Occam's razor and parsimony principles are insufficient to ground learning. Instead, we derive and demonstrate a set of relativistic principles that yield clearer insight into the nature and dynamics of learning. We show that concepts of simplicity are fundamentally contingent, that all learning operates relative to an initial guess, and that generalization cannot be measured or strongly inferred, but that it can be expected given enough observation. Using these principles, we reconstruct our understanding in terms of distributed learning systems whose components inherit beliefs and update them. We then apply this perspective to elucidate the nature of some real world inductive processes including deep learning.

Ultra-dense edge computing (UDEC) has great potential, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: i) efficient utilization of multiple 5G resources (e.g., computation, communication, storage and service resources); ii) low overhead offloading decision making and resource allocation strategies; and iii) privacy and security protection schemes. Thus, we first propose an intelligent ultra-dense edge computing (I-UDEC) framework, which integrates blockchain and Artificial Intelligence (AI) into 5G ultra-dense edge computing networks. First, we show the architecture of the framework. Then, in order to achieve real-time and low overhead computation offloading decisions and resource allocation strategies, we design a novel two-timescale deep reinforcement learning (\textit{2Ts-DRL}) approach, consisting of a fast-timescale and a slow-timescale learning process, respectively. The primary objective is to minimize the total offloading delay and network resource usage by jointly optimizing computation offloading, resource allocation and service caching placement. We also leverage federated learning (FL) to train the \textit{2Ts-DRL} model in a distributed manner, aiming to protect the edge devices' data privacy. Simulation results corroborate the effectiveness of both the \textit{2Ts-DRL} and FL in the I-UDEC framework and prove that our proposed algorithm can reduce task execution time up to 31.87%.

Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism. While existing approaches have been proposed to defend against neural fake news, they are generally constrained to the very limited setting where articles only have text and metadata such as the title and authors. In this paper, we introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles as well as conduct a series of human user study experiments based on this dataset. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies, which will serve as an effective first line of defense and a useful reference for future work in defending against machine-generated disinformation.