"Any AI smart enough to pass a Turing test is smart enough to know to fail it." Suppose you are working on a high-impact yet challenging problem of malware classification. You have a large dataset at your disposal and are able to train a machine learning classifier with an accuracy of 98%. While suppressing your excitement, you convince the team to deploy the model, as who would resist a model with such an amazing performance? Quite disappointingly, the model fails to detect threats in the real world!?

In machine learning, most tasks can be easily categorized into one of two different classes: supervised learning problems or unsupervised learning problems. In supervised learning, data has labels or classes appended to it, while in the case of unsupervised learning the data is unlabeled. Let's take a close look at why this distinction is important and look at some of the algorithms associated with each type of learning. Most machine learning tasks are in the domain of supervised learning. In supervised learning algorithms, the individual instances/data points in the dataset have a class or label assigned to them.

We release a realistic, diverse, and challenging dataset for object detection on images. The data was recorded at a beer tent in Germany and consists of 15 different categories of food and drink items. We created more than 2,500 object annotations by hand for 1,110 images captured by a video camera above the checkout. We further make available the remaining 600GB of (unlabeled) data containing days of footage. Additionally, we provide our trained models as a benchmark. Possible applications include automated checkout systems which could significantly speed up the process.

A BSTRACT We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMix-Match, is significantly more data-efficient than prior work, requiring between 5 and 16 less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93 .73% This can enable the use of large, powerful models when labeling data is expensive or inconvenient. Research on SSL has produced a diverse collection of approaches, including consistency regularization (Sajjadi et al., 2016; Laine & Aila, 2017) which encourages a model to produce the same prediction when the input is perturbed and entropy minimization (Grandvalet & Bengio, 2005) which encourages the model to output high-confidence predictions. The recently proposed "MixMatch" algorithm (Berthelot et al., 2019) combines these techniques in a unified loss function and achieves strong performance on a variety of image classification benchmarks.

Using machine learning to analyze blockchain datasets is a fascinating challenge. Beyond the incredible potential of uncovering unknown insights that help us understand the behavior of crypto-assets, blockchain datasets presents very unique challenges to a machine learning practitioner. Many of these challenges translate into major roadblocks for most traditional machine learning techniques. However, the rapid evolution of machine intelligence technologies has enabled the creation of novel machine learning methods that result very applicable to the analysis of blockchain datasets. At IntoTheBlock, we regularly experiment with these new methods to improve the efficiency of our market intelligence signals.

Generative Adversarial Networks (GAN) is an architecture introduced by Ian Goodfellow and his colleagues in 2014 for generative modeling, which is using a model to generate new samples that imitate an existing dataset. It is composed of two networks: the generator that generates new samples, and the discriminator that detects fake samples. The generator tries to fool the discriminator while the discriminator tries to detect samples synthesized by the generator. Once trained, the generator can be used to create new samples on demand. GANs have quickly become popular due to their various interesting applications such as style transfer, image-to-image translation or video generation.

Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled data. However, it is quite expensive to annotate large-scale data well. To compensate for this shortage, several seminal works are utilizing large-scale unlabeled data. In this paper, we observe that seminal works do not perform well, since the quality of pseudo labels on unlabeled data is quite poor, especially when the amount of unlabeled data is significantly larger than that of labeled data. We believe that the quality of pseudo labels is the bottleneck of adversarial learning with unlabeled data. To tackle this bottleneck, we leverage deep co-training, which trains two deep networks and encourages two networks diverged by exploiting peer's adversarial examples. Based on deep co-training, we propose robust co-training (RCT) for adversarial learning with unlabeled data. We conduct comprehensive experiments on CIFAR-10 and SVHN datasets. Empirical results demonstrate that our RCT can significantly outperform baselines (e.g., robust self-training (RST)) in both standard test accuracy and robust test accuracy w.r.t. different datasets, different network structures, and different types of adversarial training.

The recent (2019-02) demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is being embedded directly within these large models. This short paper describes an architecture through which much smaller models can also answer such questions - by making use of 'raw' external knowledge. The contribution of this work is that the methods presented here rely on unsupervised learning techniques, complementing the unsupervised training of the Language Model. The goal of this line of research is to be able to add knowledge explicitly, without extensive training.

Despite the success of supervised machine learning and deep learning, there's a school of thought that says that unsupervised learning has even greater potential. The learning of a supervised learning system is limited by its training; i.e., a supervised learning system can learn only those tasks that it's trained for. By contrast, an unsupervised system could theoretically achieve "artificial general intelligence," meaning the ability to learn any task a human can learn. If the biggest problem with supervised learning is the expense of labeling the training data, the biggest problem with unsupervised learning (where the data is not labeled) is that it often doesn't work very well. Nevertheless, unsupervised learning does have its uses: It can sometimes be good for reducing the dimensionality of a data set, exploring the pattern and structure of the data, finding groups of similar objects, and detecting outliers and other noise in the data.

Now it's time for the most exciting part of our project, from here on we are going to write our code for Generative Adversarial Network (GAN). We are going to use Keras -- A Deep Learning Library to create our GAN. Before starting let's briefly understand what is GAN and it's structure. Generative adversarial networks (GANs) are an exciting recent innovation in machine learning. It was first introduced by Ian Godfellow in his paper Generative Adversarial Networks.