This is Part 4 of the tutorial on implementing a YOLO v3 detector from scratch. In the last part, we implemented the forward pass of our network. In this part, we threshold our detections by an object confidence followed by non-maximum suppression. The code for this tutorial is designed to run on Python 3.5, and PyTorch 0.4. It can be found in it's entirety at this Github repo.

Deep Learning zoo is getting bigger by the day. This is probably due to the fact that we are "crossing the chasm" with this technology and that we are entering "early majority" phase. Simply put, people find more and more ways to use deep learning concepts and come up with different forms of neural networks. So far in our journey through this intriguing world, we covered many topics, different architectures of neural networks and types of learning. However, we explored just discriminative algorithms and not the generative ones (more on that later) and these types of algorithms are some of the most interesting cases that could be found in this neural networks universe.

The motivation for this project was for me to learn using a recurrent neural network (RNN) to generate quotes similar to my favorite philosophers and thinkers. I had seen many other people generating music, jokes and even molecules using RNNs. I was pumped to do the same, but for philosophy. From the web, I had collected about 5000 quotes from thinkers like Camus, Nietzsche, Wittgenstein, Feynman, David Hume, Stephen Hawking, and James Carse. What skipped my eye completely was that the projects that I took as inspiration usually had a dataset that went into millions and all I had with myself was 5000 sentences.

Abstract-- The present paper shows a solution to the problem of automatic distress detection, more precisely the detection of holes in paved roads. To do so, the proposed solution uses a weightless neural network known as Wisard to decide whether an image of a road has any kind of cracks. In addition, the proposed architecture also shows how the use of transfer learning was able to improve the overall accuracy of the decision system. As a verification step of the research, an experiment was carried out using images from the streets at the Federal University of Tocantins, Brazil. The architecture of the developed solution presents a result of 85.71% accuracy in the dataset, proving to be superior to approaches of the state-of-the-art. I.INTRODUCTION In Brazil, most of the traffic is driven on asphalt roads.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this paper, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or Uniform distribution. Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding on our designs. Experimental results compared among twelve algorithms for link prediction and twenty algorithms for graph clustering validate our solutions.

Abstract-- This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestrians, and train our policy using this model. Two policies that control both braking and steering are compared against a baseline where the only action taken is (conventional) braking in a straight line. The two policies are trained using two distinct reward structures, one where any and all collisions incur a fixed penalty, and a second one where the penalty is calculated based on already established delta-v models of injury severity. The results show that both policies exceed the performance of the baseline, with the policy trained using injury models having the highest performance.

Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was recently proposed as a method for assessing the similarity of the representations learned by neural networks. It has been shown that two networks with the same architecture trained from different initializations learn representations that at hidden layers show low similarity when assessed with subspace match, even when the output layers show high similarity and the networks largely exhibit similar performance on classification tasks. In this note, we present a simple example motivated by standard results in commutative algebra to illustrate how this can happen, and show that although the subspace match at a hidden layer may be 0, the representations learned may be isomorphic as vector spaces. This leads us to conclude that a subspace match comparison of learned representations may well be uninformative, and it points to the need for better methods of understanding learned representations.

Informal settlements are home to the most socially and economically vulnerable people on the planet. In order to deliver effective economic and social aid, non-government organizations (NGOs), such as the United Nations Children's Fund (UNICEF), require detailed maps of the locations of informal settlements. However, data regarding informal and formal settlements is primarily unavailable and if available is often incomplete. This is due, in part, to the cost and complexity of gathering data on a large scale. An additional complication is that the definition of an informal settlement is also very broad, which makes it a non-trivial task to collect data. This also makes it challenging to teach a machine what to look for. Due to these challenges we provide three contributions in this work. 1) A brand new machine learning data-set, purposely developed for informal settlement detection that contains a series of low and very-high resolution imagery, with accompanying ground truth annotations marking the locations of known informal settlements. 2) We demonstrate that it is possible to detect informal settlements using freely available low-resolution (LR) data, in contrast to previous studies that use very-high resolution (VHR) satellite and aerial imagery, which is typically cost-prohibitive for NGOs. 3) We demonstrate two effective classification schemes on our curated data set, one that is cost-efficient for NGOs and another that is cost-prohibitive for NGOs, but has additional utility. We integrate these schemes into a semi-automated pipeline that converts either a LR or VHR satellite image into a binary map that encodes the locations of informal settlements. We evaluate and compare our methods.

Abstract--In this work we investigate approaches to reconstruct generator models from measurements available at the generator terminal bus using machine learning (ML) techniques. The goal is to develop an emulator which is trained online and is capable of fast predictive computations. The training is illustrated on synthetic data generated based on available open-source dynamical generator model. Two ML techniques were developed and tested: (a) standard vector auto-regressive (VAR) model; and (b) novel customized long short-term memory (LSTM) deep learning model. Tradeoffs in reconstruction ability between computationally light but linear AR model and powerful but computationally demanding LSTM model are established and analyzed.

This paper introduces a novel low-cost device prototype for the automatic diagnosis of diseases, utilizing inputted symptoms and personal background. The engineering goal is to solve the problem of limited healthcare access with a single device. Diagnosing diseases automatically is an immense challenge, owing to their variable properties and symptoms. On the other hand, Neural Networks have developed into a powerful tool in the field of machine learning, one that is showing to be extremely promising at computing diagnosis even with inconsistent variables. In this research, a cheap device was created to allow for straightforward diagnosis and treatment of human diseases. By utilizing Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs), outfitted on a Raspberry Pi Zero processor ($5), the device is able to detect up to 1537 different diseases and conditions and utilize a CNN for on-device visual diagnostics. The user can input the symptoms using the buttons on the device and can take pictures using the same mechanism. The algorithm processes inputted symptoms, providing diagnosis and possible treatment options for common conditions. The purpose of this work was to be able to diagnose diseases through an affordable processor with high accuracy, as it is currently achieving an accuracy of 90% for Top-5 symptom-based diagnoses, and 91% for visual skin diseases. The NNs achieve performance far above any other tested system, and its efficiency and ease of use will prove it to be a helpful tool for people around the world. This device could potentially provide low-cost universal access to vital diagnostics and treatment options.