Machine learning is a nightmare without some kind of structure. You can't build everything from scratch, especially if you're in a business setting. Even if you want to (and if you do, comment here and tell us about it!), You need a framework to help bring your vision to life. Here are a few machine learning frameworks designed to help get those projects off the ground.

Generative adversarial networks (GANs), which were first introduced in 2014, have proven remarkably successful at generating synthetic images. A GAN consists of two networks, one that tries to produce convincing fakes, and one that tries to distinguish fakes from real examples. The two networks are trained together, and the competition between them can converge quickly on a useful generative model. In a paper that was accepted to IEEE's Winter Conference on Applications of Computer Vision, we describe a new use of GANs to generate examples of clothing that match textual product descriptions. The idea is that a shopper could use a visual guide to refine a text query until it reliably retrieved the product for which she or he was looking.

Creating complex neural networks with different architectures in Python should be a standard practice for any machine learning engineer or data scientist. But a genuine understanding of how a neural network works is equally valuable. In this article, learn the fundamentals of how you can build neural networks without the help of the frameworks that might make it easier to use. While reading the article, you can open the notebook on GitHub and run the code at the same time. In this article, I explain how to make a basic deep neural network by implementing the forward and backward pass (backpropagation). This requires some specific knowledge about the functions of neural networks, which I discuss in this introduction to neural networks.

If you can't explain it simply, you don't understand it well enough. Disclaimer: This article draws and expands upon material from (1) Christoph Molnar's excellent book on Interpretable Machine Learning which I definitely recommend to the curious reader, (2) a deep learning visualization workshop from Harvard ComputeFest 2020, as well as (3) material from CS282R at Harvard University taught by Ike Lage and Hima Lakkaraju, who are both prominent researchers in the field of interpretability and explainability. This article is meant to condense and summarize the field of interpretable machine learning to the average data scientist and to stimulate interest in the subject. Machine learning systems are becoming increasingly employed in complex high-stakes settings such as medicine (e.g. Despite this increased utilization, there is still a lack of sufficient techniques available to be able to explain and interpret the decisions of these deep learning algorithms.

Instead we should say, "Can symbols help us?" And the answer is, overwhelmingly, yes. Almost all the world's software is built on symbols. And then you have to say, "Empirically, does the deep-learning stuff do what we want it to do?" And the problem so far is it has been model free.

Canadian startup DarwinAI and researchers from the University of Waterloo are open-sourcing COVID-Net, a convolutional neural network that aims to detect COVID-19 in X-ray imagery. In response to the pandemic, a global community of health care and AI researchers have produced a number of AI systems for identifying COVID-19 in CT scans. Companies like Alibaba and AI startups RadLogics and Lunit claim they've created systems capable of recognizing COVID-19 in X-ray or CT scans with more than 90% accuracy. Early work from Chinese medical researchers and a system published in the journal Radiology last week demonstrated similar results. Like other companies making AI to detect COVID-19 from chest X-rays, DarwinAI said it's creating COVID-Net and the accompanying COVIDx data set to give doctors a way to quickly triage and screen potential cases.

A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template based approaches, but does not require domain knowledge and is much more scalable.

This paper mainly discusses the generation of personalized fonts as the problem of image style transfer. The main purpose of this paper is to design a network framework that can extract and recombine the content and style of the characters. These attempts can be used to synthesize the entire set of fonts with only a small amount of characters. The paper combines various depth networks such as Convolutional Neural Network, Multi-layer Perceptron and Residual Network to find the optimal model to extract the features of the fonts character. The result shows that those characters we have generated is very close to real characters, using Structural Similarity index and Peak Signal-to-Noise Ratio evaluation criterions.

An end-to-end solution for handwritten numeral string recognition is proposed, in which the numeral string is considered as composed of objects automatically detected and recognized by a YoLo-based model. The main contribution of this paper is to avoid heuristic-based methods for string preprocessing and segmentation, the need for task-oriented classifiers, and also the use of specific constraints related to the string length. A robust experimental protocol based on several numeral string datasets, including one composed of historical documents, has shown that the proposed method is a feasible end-to-end solution for numeral string recognition. Besides, it reduces the complexity of the string recognition task considerably since it drops out classical steps, in special preprocessing, segmentation, and a set of classifiers devoted to strings with a specific length.

Machine learning-based multi-label medical text classifications can be used to enhance the understanding of the human body and aid the need for patient care. We present a broad study on clinical natural language processing techniques to maximise a feature representing text when predicting medical codes on patients with multi-morbidity. We present results of multi-label medical text classification problems with 18, 50 and 155 labels. We compare several variations to embeddings, text tagging, and pre-processing. For imbalanced data we show that labels which occur infrequently, benefit the most from additional features incorporated in embeddings. We also show that high dimensional embeddings pre-trained using health-related data present a significant improvement in a multi-label setting, similarly to the way they improve performance for binary classification. High dimensional embeddings from this research are made available for public use.