Probabilistic time-series models become popular in the forecasting field as they help to make optimal decisions under uncertainty. Despite the growing interest, a lack of thorough analysis hinders choosing what is worth applying for the desired task. In this paper, we analyze the performance of three prominent probabilistic time-series models for sales forecasting. To remove the role of random chance in architecture's performance, we make two experimental principles; 1) Large-scale dataset with various cross-validation sets. 2) A standardized training and hyperparameter selection. The experimental results show that a simple Multi-layer Perceptron and Linear Regression outperform the probabilistic models on RMSE without any feature engineering. Overall, the probabilistic models fail to achieve better performance on point estimation, such as RMSE and MAPE, than comparably simple baselines. We analyze and discuss the performances of probabilistic time-series models.

Binary linear classification has been explored since the very early days of the machine learning literature. Perhaps the most classical algorithm is the Perceptron, where a weight vector used to classify examples is maintained, and additive updates are made as incorrect examples are discovered. The Perceptron has been thoroughly studied and several versions have been proposed over many decades. The key theoretical fact about the Perceptron is that, so long as a perfect linear classifier exists with some margin $\gamma > 0$, the number of required updates to find such a perfect linear separator is bounded by $\frac{1}{\gamma^2}$. What has never been fully addressed is: does there exist an algorithm that can achieve this with fewer updates? In this paper we answer this in the affirmative: we propose the Optimistic Perceptron algorithm, a simple procedure that finds a separating hyperplane in no more than $\frac{1}{\gamma}$ updates. We also show experimentally that this procedure can significantly outperform Perceptron.

Aiming at drastic speedup for point-feature embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptrons (MLP) and a lookup table (LUT) to transform point-coordinate inputs into high-dimensional features. When compared with PointNet's feature embedding part realized by MLP that requires millions of dot products, the proposed framework at test time requires no such layers of matrix-vector products but requires only looking up the nearest entities from the tabulated MLP followed by interpolation, defined over discrete inputs on a 3D lattice that is substantially arranged irregularly. We call this framework LUTI-MLP: LUT Interpolation ML that provides a way to train end-to-end irregularly tabulated MLP coupled to a LUT in a specific manner without the need for any approximation at test time. LUTI-MLP also provides significant speedup for Jacobian computation of the embedding function wrt global pose coordinate on Lie algebra $\mathfrak{se}(3)$ at test time, which could be used for point-set registration problems. After extensive evaluation using the ModelNet40, we confirmed that the LUTI-MLP even with a small (e.g., $4^3$) lattice yields performance comparable to that of the MLP while achieving significant speedup: $100\times$ for the embedding, $12\times$ for the approximate Jacobian, and $860\times$ for the canonical Jacobian.

Twitter is one of the top influenced social media which has a million number of active users. It is commonly used for microblogging that allows users to share messages, ideas, thoughts and many more. Thus, millions interaction such as short messages or tweets are flowing around among the twitter users discussing various topics that has been happening world-wide. This research aims to analyse a sentiment of the users towards a particular trending topic that has been actively and massively discussed at that time. We chose a hashtag \textit{\#kpujangancurang} that was the trending topic during the Indonesia presidential election in 2019. We use the hashtag to obtain a set of data from Twitter to analyse and investigate further the positive or the negative sentiment of the users from their tweets. This research utilizes rapid miner tool to generate the twitter data and comparing Naive Bayes, K-Nearest Neighbor, Decision Tree, and Multi-Layer Perceptron classification methods to classify the sentiment of the twitter data. There are overall 200 labeled data in this experiment. Overall, Naive Bayes and Multi-Layer Perceptron classification outperformed the other two methods on 11 experiments with different size of training-testing data split. The two classifiers are potential to be used in creating sentiment analyzer for low-resource languages with small corpus.

Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting". Many state-of-the-art solutions to continual learning rely on biasing and/or partitioning a model to accommodate successive tasks incrementally. However, these methods largely depend on the availability of a task-oracle to confer task identities to each test sample, without which the models are entirely unable to perform. To address this shortcoming, we propose and compare several candidate task-assigning mappers which require very little memory overhead: (1) Incremental unsupervised prototype assignment using either nearest means, Gaussian Mixture Models or fuzzy ART backbones; (2) Supervised incremental prototype assignment with fast fuzzy ARTMAP; (3) Shallow perceptron trained via a dynamic coreset. Our proposed model variants are trained either from pre-trained feature extractors or task-dependent feature embeddings of the main classifier network. We apply these pipeline variants to continual learning benchmarks, comprised of either sequences of several datasets or within one single dataset. Overall, these methods, despite their simplicity and compactness, perform very close to a ground truth oracle, especially in experiments of inter-dataset task assignment. Moreover, best-performing variants only impose an average cost of 1.7% parameter memory increase.

We consider a commonly studied supervised classification of a synthetic dataset whose labels are generated by feeding a one-layer neural network with random iid inputs. We study the generalization performances of standard classifiers in the high-dimensional regime where $\alpha=n/d$ is kept finite in the limit of a high dimension $d$ and number of samples $n$. Our contribution is three-fold: First, we prove a formula for the generalization error achieved by $\ell_2$ regularized classifiers that minimize a convex loss. This formula was first obtained by the heuristic replica method of statistical physics. Secondly, focussing on commonly used loss functions and optimizing the $\ell_2$ regularization strength, we observe that while ridge regression performance is poor, logistic and hinge regression are surprisingly able to approach the Bayes-optimal generalization error extremely closely. As $\alpha \to \infty$ they lead to Bayes-optimal rates, a fact that does not follow from predictions of margin-based generalization error bounds. Third, we design an optimal loss and regularizer that provably leads to Bayes-optimal generalization error.

Cancer has long been a main cause of human death, and the discovery of new drugs and the customization of cancer therapy have puzzled people for a long time. In order to facilitate the discovery of new anti-cancer drugs and the customization of treatment strategy, we seek to predict the response of different anti-cancer drugs with variational autoencoders (VAE) and multi-layer perceptron (MLP).Our model takes as input gene expression data of cancer cell lines and anti-cancer drug molecular data, and encode these data with {\sc {GeneVae}} model, which is an ordinary VAE, and rectified junction tree variational autoencoder ({\sc JtVae}) (\cite{jin2018junction}) model, respectively. Encoded features are processes by a Multi-layer Perceptron (MLP) model to produce a final prediction. We reach an average coefficient of determination ($R^{2} = 0.83$) in predicting drug response on breast cancer cell lines and an average $R^{2} > 0.84$ on pan-cancer cell lines. Additionally, we show that our model can generate unseen effective drug compounds for specific cancer cell lines.

We present a novel and practical deep learning pipeline termed RandomForestMLP. This core trainable classification engine consists of a convolutional neural network backbone followed by an ensemble-based multi-layer perceptrons core for the classification task. It is designed in the context of self and semi-supervised learning tasks to avoid overfitting while training on very small datasets. The paper details the architecture of the RandomForestMLP and present different strategies for neural network decision aggregation. Then, it assesses its robustness to overfitting when trained on realistic image datasets and compares its classification performance with existing regular classifiers.

A crash course in neural networks for beginners You know the difference between a multilayer perceptron and a convolutional neural network. You will be able to program your own neural network in python. Description What is machine learning / ai? How to learn machine learning in practice? "From my personal experience I can tell you that companies will actively searching for you if you aquire some skills in the data science field. Diving into this topic can not only immensly improve your career opportunities but also your job satisfaction!"