The academic Deep Learning research community has largely stayed away from the financial markets. Maybe that's because the finance industry has a bad reputation, the problem doesn't seem interesting from a research perspective, or because data is difficult and expensive to obtain. In this post, I'm going to argue that training Reinforcement Learning agents to trade in the financial (and cryptocurrency) markets can be an extremely interesting research problem. I believe that it has not received enough attention from the research community but has the potential to push the state-of-the art of many related fields. It is quite similar to training agents for multiplayer games such as DotA, and many of the same research problems carry over. Knowing virtually nothing about trading, I have spent the past few months working on a project in this field. This is not a "price prediction using Deep Learning" post. So, if you're looking for example code and models you may be disappointed. Instead, I want to talk on a more high level about why learning to trade using Machine Learning is difficult, what some of the challenges are, and where I think Reinforcement Learning fits in. If there's enough interest in this area I may follow up with another post that includes concrete examples. I expect most readers to have no background in trading, just like I didn't, so I will start out with covering some of the basics. I'm by no means an expert, so please let me know in the comments so if you find mistakes. I will use cryptocurrencies as a running example in this post, but the same concepts apply to most of the financial markets. The reason to use cryptocurrencies is that data is free, public, and easily accessible. Anyone can sign up to trade. The barriers to trading in the financial markets are a little higher, and data can be expensive.

I want to show you that Deep Convolutional Neural Nets are not nearly as intimidating as they sound. And I'll prove it by showing you an implementation of one that I made in Google Sheets. Copy it (use the File Make a copy option in top left), and you can then play around with it to see how the different levers affect the model's prediction. The rest of the article will be a short intro to understand the high level intuitions behind Convolutional Neural Nets (CNN), and then some recommended resources for further information. Before continuing, I'd like to make a shout out to FastAI.

Artificial Intelligence (AI) is the field of computer science dedicated to solving cognitive problems commonly associated with human intelligence, such as learning, problem solving, and pattern recognition. Artificial Intelligence, often abbreviated as "AI", may connote robotics or futuristic scenes, AI goes well beyond the automatons of science fiction, into the non-fiction of modern day advanced computer science. Professor Pedro Domingos, a prominent researcher in this field, describes "five tribes" of machine learning, comprised of symbolists, with origins in logic and philosophy; connectionists, stemming from neuroscience; evolutionaries, relating to evolutionary biology; Bayesians, engaged with statistics and probability; and analogizers with origins in psychology. Recently, advances in the efficiency of statistical computation have led to Bayesians being successful at furthering the field in a number of areas, under the name "machine learning". Similarly, advances in network computation have led to connectionists furthering a subfield under the name "deep learning". Machine learning (ML) and deep learning (DL) are both computer science fields derived from the discipline of Artificial Intelligence.

Artificial intelligence and machine learning have leapt off the pages of science fiction novels and burst into the real world. These technologies have game-changing implications for businesses of all sizes, whether you're planning to implement them yourself or contemplate the consequences of their adoption on the world at large. With these fields moving so fast, it's hard to stay on top of big changes, let alone smaller advances that can affect IT organizations and you personally. That's where AI and machine learning conferences come in. There's no better way to advance your career, learn new AI and ML skills, make new human connections, and maybe some non-human ones as well.

Which technologies have the greatest potential to transform the world over the next decade? Here's what developers really think about AWS, Microsoft Azure, and Google Cloud Platform providers lack adequate support resources for developers. Research and advisory firm Lux Research set out to find the answer, applying its in-house data analysis platform and the expertise of its global technical team to identify and rank the 18 most transformative technologies. The firm's newly released "18 for 2018" report covers everything "from current rock stars of innovation to hidden gem technologies." At the top of the list of potentially transformative technologies is machine learning and deep neural networks.

Networks observed in the real world like social networks, collaboration networks etc., exhibit temporal dynamics, i.e. nodes and edges appear and/or disappear over time. In this paper, we propose a generative, latent space based, statistical model for such networks (called dynamic networks). We consider the case where the number of nodes is fixed, but the presence of edges can vary over time. Our model allows the number of communities in the network to be different at different time steps. We use a neural network based methodology to perform approximate inference in the proposed model and its simplified version. Experiments done on synthetic and real-world networks for the task of community detection and link prediction demonstrate the utility and effectiveness of our model as compared to other similar existing approaches. To the best of our knowledge, this is the first work that integrates statistical modeling of dynamic networks with deep learning for community detection and link prediction.

This paper introduces a deep learning based classifier for common skin ailments, to help people without easy access to dermatologists. We have confirmed that it can classify at approximately 80% accuracy on average, when primary care doctors are reported to have 53% success as per recent literature. Dermatological diseases are common in every population and have a wide spectrum in severity. With a shortage of dermatological experts being observed in many countries, machine learning solutions can offer timely medical advice regarding existence of common skin diseases. The paper implements supervised classification of nine distinct dermatological diseases which have high occurrence in East Asian countries. Our current attempt establishes that deep learning based techniques are viable avenues for preliminary information.

Reducing labeling costs in supervised learning is a critical issue in many practical machine learning applications. In this paper, we consider positive-confidence (Pconf) classification, the problem of training a binary classifier only from positive data equipped with confidence. Pconf classification can be regarded as a discriminative extension of one-class classification (which is aimed at "describing" the positive class by clustering-related methods), with ability to tune hyper-parameters for "classifying" positive and negative samples. Pconf classification is also related to positive-unlabeled (PU) classification (which uses hard-labeled positive data and unlabeled data), but the difference is that it enables us to avoid estimating the class priors, which is a critical bottleneck in typical PU classification methods. For the Pconf classification problem, we provide a simple empirical risk minimization framework and give a formulation for linear-in-parameter models that can be implemented easily and computationally efficiently. We also theoretically establish the consistency and estimation error bound for Pconf classification, and demonstrate the practical usefulness of the proposed method for deep neural networks through experiments.

In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forgets how to solve previously learnt tasks. One of the original solutions to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of the previous task/s. This is very effective for simple tasks. However, pseudo-rehearsal has not yet been successfully applied to very complex tasks because in these tasks it is difficult to generate representative items. We accomplish pseudo-rehearsal by using a Generative Adversarial Network to generate items so that our deep network can learn to sequentially classify the CIFAR-10, SVHN and MNIST datasets. After training on all tasks, our network loses only 1.67% absolute accuracy on CIFAR-10 and gains 0.24% absolute accuracy on SVHN. Our model's performance is a substantial improvement compared to the current state of the art solution.

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the net- work to identify neurons with high influence on the property and distribution of interest using an axiomatically justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by training convolutional neural net- works on MNIST, ImageNet, Pubfig, and Diabetic Retinopathy datasets. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) help extract the essence of what the network learned about a class, (3) isolate individual features the network uses to make decisions and distinguish related instances, and (4) assist in understanding misclassifications.