Weaknesses: The paper is not very novel or significant in its contribution. It compiles two regularization methods to mitigate two long-standing problems in differentiable NAS, however, the proposed methods are not very novel. NAS-Bench is not a very well established benchmark that not many people are very familiar with. It is not fair to compare with existing work on NAS-bench, as most of them were not optimized on NAS-Bench. For instance, the DARTS work may work equally well with proper hyperparameter tuning and regularization. With the existing DARTS hyperparmeters, search on NAS-bench converges to networks with only identity/skip operation.

Speech Emotion Recognition (SER) is a challenging task. In this paper, we introduce a modality conversion concept aimed at enhancing emotion recognition performance on the MELD dataset. We assess our approach through two experiments: first, a method named Modality-Conversion that employs automatic speech recognition (ASR) systems, followed by a text classifier; second, we assume perfect ASR output and investigate the impact of modality conversion on SER, this method is called Modality-Conversion++. Our findings indicate that the first method yields substantial results, while the second method outperforms state-of-the-art (SOTA) speech-based approaches in terms of SER weighted-F1 (WF1) score on the MELD dataset. This research highlights the potential of modality conversion for tasks that can be conducted in alternative modalities.

In recent years, the Python programming language has seen a huge user base. One of the reasons could be that it is easier to learn as compared to other object-oriented programming languages like Java, C, C#, JavaScript, and therefore more and more beginners who are entering the field of computer science are opting for Python. Another reason why the popularity of Python has shot up is that it is used in almost all domains of the IT industry, be it data science, machine learning, automation, web scraping, artificial intelligence, cyber-security, cloud computing, and what not! According to the recent developer survey, it is seen that Python is currently the second most loved programming language after JavaScript and will easily shoot up in the coming years. Demand for Python developers has significantly risen, especially in the past few months, and therefore learning Python could get you some really good career options.

In the paper, we test two different approaches to the {unsupervised} word sense disambiguation task for Polish. In both methods, we use neural language models to predict words similar to those being disambiguated and, on the basis of these words, we predict the partition of word senses in different ways. In the first method, we cluster selected similar words, while in the second, we cluster vectors representing their subsets. The evaluation was carried out on texts annotated with plWordNet senses and provided a relatively good result (F1=0.68 for all ambiguous words). The results are significantly better than those obtained for the neural model-based unsupervised method proposed in \cite{waw:myk:17:Sense} and are at the level of the supervised method presented there. The proposed method may be a way of solving word sense disambiguation problem for languages that lack sense annotated data.

Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition.

So how can I get the result of the arithmetic expression, e? Well, there are two ways: (i) if I'm lucky, and lazy (think: efficiency) I could have the value of e stored (as data) in some hashtable (a data dictionary) where I can use a key to pick-up the value of e anytime I need it (figure 1); The first method, let's call it the data/memorization method, does not require us to know how to compute e. That is, if the value of e is not memorized (and stored in some data storage), then the only way to get the value of e is to know that adding m to n is essentially adding n 1's to m and knowing that multiplying m by n is adding m to itself n times (and thus'multiplication' can be defined only after the more primitive function'addition' is defined). Crucially, then, the first method is limited to the data I have seen and memorized (i.e., stored in memory), while the second method does not have this limitation -- in fact, once I know the procedures of addition and multiplication (and other operations) then I'm ready for an infinite number of expressions. So we could, at this early juncture, describe the first method by "knowing what (is the value)" and the second method by "knowing how (to compute the value)" -- the first is fast (not to mention easy) but limited to the data I have seen and memorized (stored). The second is not limited to the data we have seen, but requires detailed knowledge (knowing how) of the procedures.

The aim of this paper is to select the RBF neural network centers under concurrent faults. It is well known that fault tolerance is a very attractive property for neural network algorithms. And center selection is an important procedure during the training process of RBF neural network. In this paper, we will address these two issues simultaneously and devise two novel algorithms. Both of them are based on the framework of ADMM and utilize the technique of sparse approximation. For both two methods, we first define a fault tolerant objective function. After that, the first method introduces the MCP function (an approximate l0-norm function) and combine it with ADMM framework to select the RBF centers. While the second method utilize ADMM and IHT to solve the problem. The convergence of both two methods is proved. Simulation results show that the proposed algorithms are superior to many existing center selection algorithms under concurrent fault.