Despite being quite effective in a variety of tasks across industries, deep learning is constantly evolving, proposing new neural network (NN) architectures, deep learning (DL) tasks, and even brand new concepts of the next generation of NNs, such as the Spiking Neural Network (SNN). SNN was introduced by the researchers at Heidelberg University and the University of Bern developing as a fast and energy-efficient technique for computing using spiking neuromorphic substrates. In this article, we will mostly discuss Spiking Neural Network as a variant of neural network. We will also try to understand how is it different from the traditional neural networks. Below is a list of the important topics to be tackled.

Graph neural networks (GNNs) have demonstrated superior performance for semisupervised node classification on graphs, as a result of their ability to exploit node features and topological information simultaneously. However, most GNNs implicitly assume that the labels of nodes and their neighbors in a graph are the same or consistent, which does not hold in heterophilic graphs, where the labels of linked nodes are likely to differ. Hence, when the topology is non-informative for label prediction, ordinary GNNs may work significantly worse than simply applying multi-layer perceptrons (MLPs) on each node. GNN, whose message passing mechanism is derived from a discrete regularization framework and could be theoretically explained as an approximation of a polynomial graph filter defined on the spectral domain of p-Laplacians. GNNs significantly outperform several state-of-the-art GNN architectures on heterophilic benchmarks while achieving competitive performance on homophilic benchmarks. GNNs can adaptively learn aggregation weights and are robust to noisy edges. In this paper, we explore the usage of graph neural networks (GNNs) for semi-supervised node classification on graphs, especially when the graphs admit strong heterophily or noisy edges. Semisupervised learning problems on graphs are ubiquitous in a lot of real-world scenarios, such as user classification in social media (Kipf & Welling, 2017), protein classification in biology (Velickovic et al., 2018), molecular property prediction in chemistry (Duvenaud et al., 2015), and many others (Marcheggiani & Titov, 2017; Satorras & Estrach, 2018). Recently, GNNs are becoming the de facto choice for processing graph structured data.

If you are new to the field of Deep Learning, I encourage you to read my previous article about Understand Deep Leaning with Simple exercise-PyTorch which will give you a precise understanding of how neural networks works in general. This article is a more deep dive into the internal working of Neuron/Perceptron which is the building block of Deep Learning Neural Networks architecture. A human brain has billions of neurons. Neurons are interconnected nerve cells in the human brain that are involved in the processing and transmitting chemical and electrical signals. Dendrites are branches that receive information from other neurons.

Identifying the relations between chemicals and proteins is an important text mining task. BioCreative VII track 1 DrugProt task aims to promote the development and evaluation of systems that can automatically detect relations between chemical compounds/drugs and genes/proteins in PubMed abstracts. In this paper, we describe our submission, which is an ensemble system, including multiple BERT-based language models. We combine the outputs of individual models using majority voting and multilayer perceptron. Our system obtained 0.7708 in precision and 0.7770 in recall, for an F1 score of 0.7739, demonstrating the effectiveness of using ensembles of BERT-based language models for automatically detecting relations between chemicals and proteins. Our code is available at https://github.com/bionlplab/drugprot_bcvii.

The pervasiveness of GPS-enabled mobile devices and the widespread use of location-based services have resulted in the generation of massive amounts of geo-tagged data. In recent times, the data analysis now has access to more sources, including reviews, news, and images, which also raises questions about the reliability of Point-of-Interest (POI) data sources. While previous research attempted to detect fake POI data through various security mechanisms, the current work attempts to capture the fake POI data in a much simpler way. The proposed work is focused on supervised learning methods and their capability to find hidden patterns in location-based data. The ground truth labels are obtained through real-world data, and the fake data is generated using an API, so we get a dataset with both the real and fake labels on the location data. The objective is to predict the truth about a POI using the Multi-Layer Perceptron (MLP) method. In the proposed work, MLP based on data classification technique is used to classify location data accurately. The proposed method is compared with traditional classification and robust and recent deep neural methods. The results show that the proposed method is better than the baseline methods.

Human emotion recognition is an important issue in human-computer interactions and electroencephalograph (EEG) has been widely applied to emotion recognition due to its high reliability. In recent years, methods based deep learning technology have reached the state of art performance in EEG-based emotion recognition. However, there exist singularities in the parameter space of deep neural networks, which may dramatically slow down the training process. It is very worthy to investigate the specific influence of singularities when applying deep neural networks to EEG-based emotion recognition. In this paper, we mainly focus on this problem, and analyse the singular learning dynamics of deep multilayer perceptrons theoretically and numerically. The results can help us to design better algorithms to overcome the serious influence of singularities in deep neural networks for EEG-based emotion recognition.

We establish a broad methodological foundation for mixed-integer optimization with learned constraints. We propose an end-to-end pipeline for data-driven decision making in which constraints and objectives are directly learned from data using machine learning, and the trained models are embedded in an optimization formulation. We exploit the mixed-integer optimization-representability of many machine learning methods, including linear models, decision trees, ensembles, and multi-layer perceptrons. The consideration of multiple methods allows us to capture various underlying relationships between decisions, contextual variables, and outcomes. We also characterize a decision trust region using the convex hull of the observations, to ensure credible recommendations and avoid extrapolation. We efficiently incorporate this representation using column generation and clustering. In combination with domain-driven constraints and objective terms, the embedded models and trust region define a mixed-integer optimization problem for prescription generation. We implement this framework as a Python package (OptiCL) for practitioners. We demonstrate the method in both chemotherapy optimization and World Food Programme planning. The case studies illustrate the benefit of the framework in generating high-quality prescriptions, the value added by the trust region, the incorporation of multiple machine learning methods, and the inclusion of multiple learned constraints.

It was recently shown that almost all solutions in the symmetric binary perceptron are isolated, even at low constraint densities, suggesting that finding typical solutions is hard. In contrast, some algorithms have been shown empirically to succeed in finding solutions at low density. This phenomenon has been justified numerically by the existence of subdominant and dense connected regions of solutions, which are accessible by simple learning algorithms. In this paper, we establish formally such a phenomenon for both the symmetric and asymmetric binary perceptrons. We show that at low constraint density (equivalently for overparametrized perceptrons), there exists indeed a subdominant connected cluster of solutions with almost maximal diameter, and that an efficient multiscale majority algorithm can find solutions in such a cluster with high probability, settling in particular an open problem posed by Perkins-Xu '21. In addition, even close to the critical threshold, we show that there exist clusters of linear diameter for the symmetric perceptron, as well as for the asymmetric perceptron under additional assumptions.

Gradient descent during the learning process of a neural network can be subject to many instabilities. The spectral density of the Jacobian is a key component for analyzing robustness. Following the works of Pennington et al., such Jacobians are modeled using free multiplicative convolutions from Free Probability Theory. We present a reliable and very fast method for computing the associated spectral densities. This method has a controlled and proven convergence. Our technique is based on an adaptative Newton-Raphson scheme, by finding and chaining basins of attraction: the Newton algorithm finds contiguous lilypad-like basins and steps from one to the next, heading towards the objective. We demonstrate the applicability of our method by using it to assess how the learning process is affected by network depth, layer widths and initialization choices: empirically, final test losses are very correlated to our Free Probability metrics.

Most current affect scales and sentiment analysis on written text focus on quantifying valence (sentiment) -- the most primary dimension of emotion. However, emotions are broader and more complex than valence. Distinguishing negative emotions of similar valence could be important in contexts such as mental health. This project proposes a semi-supervised machine learning model (DASentimental) to extract depression, anxiety and stress from written text. First, we trained the model to spot how sequences of recalled emotion words by $N=200$ individuals correlated with their responses to the Depression Anxiety Stress Scale (DASS-21). Within the framework of cognitive network science, we model every list of recalled emotions as a walk over a networked mental representation of semantic memory, with emotions connected according to free associations in people's memory. Among several tested machine learning approaches, we find that a multilayer perceptron neural network trained on word sequences and semantic network distances can achieve state-of-art, cross-validated predictions for depression ($R = 0.7$), anxiety ($R = 0.44$) and stress ($R = 0.52$). Though limited by sample size, this first-of-its-kind approach enables quantitative explorations of key semantic dimensions behind DAS levels. We find that semantic distances between recalled emotions and the dyad "sad-happy" are crucial features for estimating depression levels but are less important for anxiety and stress. We also find that semantic distance of recalls from "fear" can boost the prediction of anxiety but it becomes redundant when the "sad-happy" dyad is considered. Adopting DASentimental as a semi-supervised learning tool to estimate DAS in text, we apply it to a dataset of 142 suicide notes. We conclude by discussing key directions for future research enabled by artificial intelligence detecting stress, anxiety and depression.