#### Evaluation of Machine Learning Fameworks on Finis Terrae II

Machine Learning (ML) and Deep Learning (DL) are two technologies used to extract representations of the data for a specific purpose. ML algorithms take a set of data as input to generate one or several predictions. To define the final version of one model, usually there is an initial step devoted …

#### Cooperative Multi-Agent Reinforcement Learning for Low-Level Wireless Communication

Traditional radio systems are strictly co-designed on the lower levels of the OSI stack for compatibility and efficiency. Although this has enabled the success of radio communications, it has also introduced lengthy standardization processes and imposed static allocation of the radio spectrum. Vari…

#### Fix your classifier: the marginal value of training the last weight layer

Neural networks are commonly used as models for classification for a wide variety of tasks. Typically, a learned affine transformation is placed at the end of such models, yielding a per-class value used for classification. This classifier can have a vast number of parameters, which grows linearly …

#### A Bio-inspired Collision Detecotr for Small Quadcopter

Sense and avoid capability enables insects to fly versatilely and robustly in dynamic complex environment. Their biological principles are so practical and efficient that inspired we human imitating them in our flying machines. In this paper, we studied a novel bio-inspired collision detector and i…

#### Non-Parametric Transformation Networks

ConvNets have been very effective in many applications where it is required to learn invariances to within-class nuisance transformations. However, through their architecture, ConvNets only enforce invariance to translation. In this paper, we introduce a new class of convolutional architectures cal…

#### Novel Methods for Enhancing the Performance of Genetic Algorithms

In this thesis we propose new methods for crossover operator namely: cut on worst gene (COWGC), cut on worst L+R gene (COWLRGC) and Collision Crossovers. And also we propose several types of mutation operator such as: worst gene with random gene mutation (WGWRGM) , worst LR gene with random gene mu…

#### A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation

We describe recurrent neural networks (RNNs), which have attracted great attention on sequential tasks, such as handwriting recognition, speech recognition and image to text. However, compared to general feedforward neural networks, RNNs have feedback loops, which makes it a little hard to understa…

#### Brain EEG Time Series Selection: A Novel Graph-Based Approach for Classification

Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this pap…

#### Accelerated Alternating Projections for Robust Principal Component Analysis

We study robust PCA for the fully observed setting, which is about separating a low rank matrix $boldsymbol{L}$ and a sparse matrix $boldsymbol{S}$ from their sum $boldsymbol{D}=boldsymbol{L}+boldsymbol{S}$. In this paper, a new algorithm, dubbed accelerated alternating projections, is introduced f…

#### Multivariate LSTM-FCNs for Time Series Classification

Over the past decade, multivariate time series classification has been receiving a lot of attention. We propose augmenting the existing univariate time series classification models, LSTM-FCN and ALSTM-FCN with a squeeze and excitation block to further improve performance. Our proposed models outper…

#### High Dimensional Spaces, Deep Learning and Adversarial Examples

In this paper, we analyze deep learning from a mathematical point of view and derive several novel results. The results are based on intriguing mathematical properties of high dimensional spaces. We first look at perturbation based adversarial examples and show how they can be understood using topo…

#### An Explicit Convergence Rate for Nesterov’s Method from SDP

The framework of Integral Quadratic Constraints (IQC) introduced by Lessard et al. (2014) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to semi-definite programming (SDP). In particular, this technique was applied to Nesterov’s accelerated …

#### An Explicit Convergence Rate for Nesterov’s Method from SDP

The framework of Integral Quadratic Constraints (IQC) introduced by Lessard et al. (2014) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to semi-definite programming (SDP). In particular, this technique was applied to Nesterov’s accelerated …

#### Better Runtime Guarantees Via Stochastic Domination

Apart from few exceptions, the mathematical runtime analysis of evolutionary algorithms is mostly concerned with expected runtimes. In this work, we argue that stochastic domination is a notion that should be used more frequently in this area. Stochastic domination allows to formulate much more inf…

#### Can Computers Create Art?

This paper discusses whether computers, using Artifical Intelligence (AI), could create art. The first part concerns AI-based tools for assisting with art making. The history of technologies that automated aspects of art is covered, including photography and animation. In each case, we see initial …

#### Phase Retrieval via Randomized Kaczmarz: Theoretical Guarantees

We consider the problem of phase retrieval, i.e. that of solving systems of quadratic equations. A simple variant of the randomized Kaczmarz method was recently proposed for phase retrieval, and it was shown numerically to have a computational edge over state-of-the-art Wirtinger flow methods. In t…

#### Using probabilistic programs as proposals

Monte Carlo inference has asymptotic guarantees, but can be slow when using generic proposals. Handcrafted proposals that rely on user knowledge about the posterior distribution can be efficient, but are difficult to derive and implement. This paper proposes to let users express their posterior kno…

#### Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition

audio Convolutional Neural Network DNN RNN speech

Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech. How…

#### MEBoost: Mixing Estimators with Boosting for Imbalanced Data Classification

Class imbalance problem has been a challenging research problem in the fields of machine learning and data mining as most real life datasets are imbalanced. Several existing machine learning algorithms try to maximize the accuracy classification by correctly identifying majority class samples while…

#### Gradient descent GAN optimization is locally stable

game Generative Adversarial Network gradient

Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the “gradient descent” form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in bot…

#### Towards a more efficient representation of imputation operators in TPOT

Automated Machine Learning encompasses a set of meta-algorithms intended to design and apply machine learning techniques (e.g., model selection, hyperparameter tuning, model assessment, etc.). TPOT, a software for optimizing machine learning pipelines based on genetic programming (GP), is a novel e…

#### On the convergence properties of GAN training

Generative Adversarial Network gradient

Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this note we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical counterexample showing that in the more realistic case of distribu…

#### A Survey on Compiler Autotuning using Machine Learning

Since the mid-1990s, researchers have been trying to use machine-learning based approaches to solve a number of different compiler optimization problems. These techniques primarily enhance the quality of the obtained results and, more importantly, make it feasible to tackle two main compiler optimi…

#### Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

Convolutional Neural Network DNN

Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for tempora…

#### Convexification of Neural Graph

Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms and functions. Iteratively, propagating from node to node alo…