Score-based models have recently been introduced as a richer framework to model distributions in high dimensions and are generally more suitable for generative tasks. In score-based models, a generative task is formulated using a parametric model (such as a neural network) to directly learn the gradient of such high dimensional distributions, instead of the density functions themselves, as is done traditionally. From the mathematical point of view, such gradient information can be utilized in reverse by stochastic sampling to generate diverse samples. However, from a computational perspective, existing score-based models can be efficiently trained only if the forward or the corruption process can be computed in closed form. By using the relationship between the process and layers in a feed-forward network, we derive a backpropagation-based procedure which we call Intermediate Generator Optimization to utilize intermediate iterates of the process with negligible computational overhead. The main advantage of IGO is that it can be incorporated into any standard autoencoder pipeline for the generative task. We analyze the sample complexity properties of IGO to solve downstream tasks like Generative PCA. We show applications of the IGO on two dense predictive tasks viz., image extrapolation, and point cloud denoising. Our experiments indicate that obtaining an ensemble of generators for various time points is possible using first-order methods.

Marine cloud brightening (MCB) is a proposed climate intervention technology to partially offset greenhouse gas warming and possibly avoid crossing climate tipping points. The impacts of MCB on regional climate are typically estimated using computationally expensive Earth System Model (ESM) simulations, preventing a thorough assessment of the large possibility space of potential MCB interventions. Here, we describe an AI model, named AiBEDO, that can be used to rapidly projects climate responses to forcings via a novel application of the Fluctuation-Dissipation Theorem (FDT). AiBEDO is a Multilayer Perceptron (MLP) model that uses maps monthly-mean radiation anomalies to surface climate anomalies at a range of time lags. By leveraging a large existing dataset of ESM simulations containing internal climate noise, we use AiBEDO to construct an FDT operator that successfully projects climate responses to MCB forcing, when evaluated against ESM simulations. We propose that AiBEDO-FDT can be used to optimize MCB forcing patterns to reduce tipping point risks while minimizing negative side effects in other parts of the climate.

We study on-line gradient-descent learning in multilayer networks analytically and numerically. The training is based on randomly drawn inputs and their corresponding outputs as defined by a target rule. In the thermodynamic limit we derive deterministic differential equations for the order parameters of the problem which allow an exact calculation of the evolution of the generalization error. First we consider a single-layer perceptron with sigmoidal activation function learning a target rule defined by a network of the same architecture. For this model the generalization error decays exponentially with the number of training examples if the learning rate is sufficiently small.

Purpose: The purpose of this study is to predict dropouts in two runs of the same MOOC using an explainable machine learning approach. With the explainable approach, we aim to enable the interpretation of the black-box predictive models from a pedagogical perspective and to produce actionable insights for related educational interventions. The similarity and the differences in feature importance between the predictive models were also examined. Design/Methodology/Approach: This is a quantitative study performed on a large public dataset containing activity logs in a MOOC. In total, 21 features were generated and standardized before the analysis. Multi-layer perceptron neural network was used as the black-box machine learning algorithm to build the predictive models.

Plant biomass estimation is critical due to the variability of different environmental factors and crop management practices associated with it. The assessment is largely impacted by the accurate prediction of different environmental sustainability indicators. A robust model to predict sustainability indicators is a must for the biomass community. This study proposes a robust model for biomass sustainability prediction by analyzing sustainability indicators using machine learning models. The prospect of ensemble learning was also investigated to analyze the regression problem. All experiments were carried out on a crop residue data from the Ohio state. Ten machine learning models, namely, linear regression, ridge regression, multilayer perceptron, k-nearest neighbors, support vector machine, decision tree, gradient boosting, random forest, stacking and voting, were analyzed to estimate three biomass sustainability indicators, namely soil erosion factor, soil conditioning index, and organic matter factor. The performance of the model was assessed using cross-correlation (R2), root mean squared error and mean absolute error metrics. The results showed that Random Forest was the best performing model to assess sustainability indicators. The analyzed model can now serve as a guide for assessing sustainability indicators in real time.

Hit song prediction, one of the emerging fields in music information retrieval (MIR), remains a considerable challenge. Being able to understand what makes a given song a hit is clearly beneficial to the whole music industry. Previous approaches to hit song prediction have focused on using audio features of a record. This study aims to improve the prediction result of the top 10 hits among Billboard Hot 100 songs using more alternative metadata, including song audio features provided by Spotify, song lyrics, and novel metadata-based features (title topic, popularity continuity and genre class). Five machine learning approaches are applied, including: k-nearest neighbours, Naive Bayes, Random Forest, Logistic Regression and Multilayer Perceptron. Our results show that Random Forest (RF) and Logistic Regression (LR) with all features (including novel features, song audio features and lyrics features) outperforms other models, achieving 89.1% and 87.2% accuracy, and 0.91 and 0.93 AUC, respectively. Our findings also demonstrate the utility of our novel music metadata features, which contributed most to the models' discriminative performance.

Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled datasets. Meanwhile, Neural Architecture Search (NAS) is becoming increasingly important as a technique to discover novel deep learning architectures. However, early NAS methods based on reinforcement learning or evolutionary algorithms suffered from ludicrous computational and memory costs. In contrast, differentiable NAS, a gradient-based approach, has the advantage of being much more efficient and has thus retained most of the attention in the past few years. In this article, we present NASiam, a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e.g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines. We crafted a search space designed explicitly for multilayer perceptrons, inside which we explored several alternatives to the standard ReLU activation function. We show that these new architectures allow ResNet backbone convolutional models to learn strong representations efficiently. NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours. We discuss the composition of the NAS-discovered architectures and emit hypotheses on why they manage to prevent collapsing behavior. Our code is available at https://github.com/aheuillet/NASiam.

We establish estimations for the parameters of the output distribution for the softmax activation function using the probit function. As an application, we develop a new efficient Bayesian learning algorithm for fully connected neural networks, where training and predictions are performed within the Bayesian inference framework in closed-form. This approach allows sequential learning and requires no computationally expensive gradient calculation and Monte Carlo sampling. Our work generalizes the Bayesian algorithm for a single perceptron for binary classification in \cite{H} to multi-layer perceptrons for multi-class classification.

Iam often amazed at how the greatest technologies were inspired by nature. The sonar was inspired by dolphins and bats, airplanes were inspired by birds. The perceptron was inspired by the neurons in our brains. The perceptron is the cornerstone of neural networks and therefore of Deep Learning. Understanding it allows us to grasp the concepts underlying machine learning algorithms.

In this tutorial, we will build a custom Perceptron from scratch, then test it on the overused Iris dataset;). I assume that you have a theoretical understanding of the Perceptron. If not, please refer to my previous article: Perceptron: The Cornerstone of Neural Networks. Now let's build that Perceptron. We will follow the same steps as the figure above.