Incrementally training deep neural networks to recognize new classes is a challenging problem. Most existing class-incremental learning methods store data or use generative replay, both of which have drawbacks, while 'rehearsal-free' alternatives such as parameter regularization or bias-correction methods do not consistently achieve high performance. Here, we put forward a new strategy for class-incremental learning: generative classification. Rather than directly learning the conditional distribution p(y|x), our proposal is to learn the joint distribution p(x,y), factorized as p(x|y)p(y), and to perform classification using Bayes' rule. As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned and by using importance sampling to estimate the likelihoods p(x|y). This simple approach performs very well on a diverse set of continual learning benchmarks, outperforming generative replay and other existing baselines that do not store data.

Chartbusters is a global challenge in which developers use AWS DeepComposer to create original compositions and compete in monthly challenges to showcase their machine learning (ML) and generative artificial intelligence (AI) skills. Regardless of your background in music or ML, one of the two new challenges will be right for you. You can choose between two different challenges this season. In the basic challenge, Melody-Go-Round, you can use any of the generative AI models available in the AWS DeepComposer Music studio to create new compositions. In the advanced challenge, Melody Harvest, you train a custom generative AI model with your own dataset using Amazon SageMaker.

Humans are a species of inventors. The world offers us raw material that we transform with skillful crafting. Technology has created innumerable tools and devices: The wheel, the printing press, the steam engine, cars, electricity, the internet… These inventions have shaped, and still do, our civilization and culture. One of our latest technological children is artificial intelligence, a tool that has become intertwined with our lives in recent years. Its impact on our society is outstanding and it's expected to keep growing in the next decades.

Counterfeiting is a big business. Nearly $509 billion of fake and pirated products were sold internationally in 2016. In that year, the latest for which data was available, counterfeit goods made up 3.3% of international trade, up from 2.5% three years earlier, according to the Organization for Economic Cooperation and Development. That figure, which does not include domestic trade in fakes, not only means companies are losing revenue and consumers are not getting their money's worth; counterfeiting also helps fund organized crime. Because it skirts safety regulations, makers of counterfeits could use toxic materials or produce unsafe products.

There are a dozen artificial intelligence conferences where researchers push the boundaries of science and show how neural networks and deep learning architectures can take on new challenges in areas such as computer vision and natural language processing. But using machine learning in real-world applications and business problems--often referred to as "applied machine learning" or "applied AI"--presents challenges that are absent in academic and scientific research settings. Applied machine learning requires resources, skills, and knowledge that go beyond data science, that can integrate AI algorithms into applications used by thousands and millions of people every day. Alyssa Simpson Rochwerger and Wilson Pang, two experienced practitioners of applied machine learning, discuss these challenges in their new book Real World AI: A Practical Guide for Responsible Machine learning. Rochwerger, a former director of product at IBM Watson, and Pang, the CTO of Appen, draw on their personal experience and knowledge to provide many examples of how organizations succeeded or failed in integrating machine learning into their products and business models.

The tiny world of biomolecules is rich in fascinating interactions between a plethora of different agents such as intricate nanomachines (proteins), shape-shifting vessels (lipid complexes), chains of vital information (DNA) and energy fuel (carbohydrates). Yet the ways in which biomolecules meet and interact to define the symphony of life is exceedingly complex. Scientists at the Bionanophotonic Systems Laboratory in EPFL's School of Engineering have developed a biosensor that can be used to observe all major biomolecule classes of the nanoworld without disturbing them. Their innovative technique uses nanotechnology, metasurfaces, infrared light and artificial intelligence. The team's research has been published in Advanced Materials.

Tensorflow and Pytorch are the two most widely used libraries in deep learning. Both these libraries have different approaches when it comes to implementing neural networks. Both these libraries started with major differences. Usually, TF was more preferred for developing production-ready models due to its better optimizations, and Pytorch was preferred for research works due to its more "pythonic" syntax and eager execution. But with Torchscript and TF 2.0, the gap between the two libraries has shrunk.

Neurocle aims to enable anyone to use artificial intelligence or AI technology. We focus on the field of deep learning vision, in particular.

Now it's time to take a look at a Korean business bringing about changes in the global economy with some new ideas. Today, we're going to introduce you to Neurocle, a developer of deep learning solutions for non-professionals. Let's hear from company CEO Lee Hong-suk (이홍석). Neurocle aims to enable anyone to use artificial intelligence or AI technology. We focus on the field of deep learning vision, in particular.

Entity Embed is based on and is a special case of the AutoBlock model described by Amazon. It allows you to transform entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors. Using Entity Embed, you can train a deep learning model to transform records into vectors in an N-dimensional embedding space. Thanks to a contrastive loss, those vectors are organized to keep similar records close and dissimilar records far apart in this embedding space. Embedding records enables scalable ANN search, which means finding thousands of candidate duplicate pairs of records per second per CPU.