Many important problems in the real world don't have unique solutions. It is thus important for machine learning models to be capable of proposing different plausible solutions with meaningful probability measures. In this work we introduce such a deep learning framework that learns the one-to-many mappings between the inputs and outputs, together with faithful uncertainty measures. We call our framework {\it modal uncertainty estimation} since we model the one-to-many mappings to be generated through a set of discrete latent variables, each representing a latent mode hypothesis that explains the corresponding type of input-output relationship. The discrete nature of the latent representations thus allows us to estimate for any input the conditional probability distribution of the outputs very effectively. Both the discrete latent space and its uncertainty estimation are jointly learned during training. We motivate our use of discrete latent space through the multi-modal posterior collapse problem in current conditional generative models, then develop the theoretical background, and extensively validate our method on both synthetic and realistic tasks. Our framework demonstrates significantly more accurate uncertainty estimation than the current state-of-the-art methods, and is informative and convenient for practical use.

A system identification based approach to neural network model replication is presented and the application of model replication to verification of fundamental, single hidden layer, neural network systems is demonstrated. The presented approach serves as a means to partially address the problem of verifying that a neural network implementation meets a provided specification given only grey-box access to the implemented network. The procedure developed involves stimulating a neural network with a chosen signal, extracting a replicated model from the response, and systematically checking that the replicated model is output-equivalent to a specified model in order to verify that the grey-box system under test is implemented to specification without direct access to its hidden parameters. The replication step is introduced to provide an inherent guarantee that the stimulus signals employed yield sufficient test coverage. This method is investigated as a neural network focused nonlinear counterpart to the traditional verification of circuits through system identification. A strategy for choosing the stimulus is provided and an algorithm for verifying that the resulting response is indicative of a specification-compliant neural network system under test is derived. We find that the method can reliably detect defects in small neural networks or in small sub-circuits within larger neural networks.

To human observers, the following two images are identical. But researchers at Google showed in 2015 that a popular object detection algorithm classified the left image as "panda" and the right one as "gibbon." And oddly enough, it had more confidence in the gibbon image. The algorithm in question was GoogLeNet, a convolutional neural network architecture that won the 2014 ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2014). The right image is an "adversarial example."

If you are a cineast, you should probably know Thomas Flight (https://www.thomasflight.com/) Recently he published another essay -- something new in this format. Basically, it was as usually about cinema, as usually with his mesmerizing and inspiring voice-over, as usually convincing and enthralling, as usually about fiction, meta-level and their collisions. Entire script of this video essay was written by AI. He used GPT-2 model for Natural Language Processing (developed by OpenAI).

I typically think of the dog days of summer as a time when news slows down. It's typically when a lot of people take time off work, and the lull leads local news stations to cover inconsequential things like cat shows or a little baby squirrel on a little baby Jet Ski. But these are not typical times. Fallout surrounding issues of bias and discrimination continues at Facebook, as multiple news outlets reported that Instagram's content moderation algorithm was 50% more likely to flag and disable the accounts of Black users than White users. Facebook and Instagram are now creating teams to examine how algorithms impact the experiences of Black, Latinx, and other specific groups of users.

The ability to provide a natural experience requires not only understanding individual words and sentences, but also the ability to respond to a wide range of conversational phrases and unexpected turns. We are adopting deep neural networks (DNNs) to improve Alexa's natural language understanding (NLU) of individual words and sentences. We've begun applying the technology to custom skills and are excited by the early results: although it will vary by use case, we expect skills that use our DNN-based NLU to realize an average of 15% improvement in accuracy. Even better, you don't have to make any changes to your skill to benefit; your skill's accuracy will improve automatically once included in the rollout. Alexa Conversations (beta) is a new AI-driven approach to dialog management that enables you to create skills that customers can interact with in a natural, unconstrained way - using the phrases they prefer, in the order they prefer – while freeing you to focus on the highest value parts of your experience.

It could be evidence that artificial intelligence has made a great leap forward and human writers and software developers will soon be redundant. Or maybe it is just the latest example of the hype getting way ahead of the reality? On this week's Tech Tent we find out what the big fuss is about something called GPT-3. OpenAI is a Californian company started in 2015 with a high-minded mission - to ensure that artificial general intelligence systems that could outperform humans in most jobs would benefit all humanity. It was founded as a non-profit with generous donations from Elon Musk among others but was quickly transformed into a for-profit business, with Microsoft investing $1bn.

It could be evidence that artificial intelligence has made a great leap forward and human writers and software developers will soon be redundant. Or maybe it is just the latest example of the hype getting way ahead of the reality? On this week's Tech Tent we find out what the big fuss is about something called GPT-3. OpenAI is a Californian company started in 2015 with a high-minded mission - to ensure that artificial general intelligence systems that could outperform humans in most jobs would benefit all humanity. It was founded as a non-profit with generous donations from Elon Musk among others but was quickly transformed into a for-profit business, with Microsoft investing $1bn.

These promising results indicate that the deep learning system has the potential to support expert-level diagnoses and expand access to high-quality cancer care. To evaluate if it could improve the accuracy and consistency of prostate cancer diagnoses, this technology needs to be validated as an assistive tool in further clinical studies and on larger and more diverse patient groups. However, we believe that AI-based tools could help pathologists in their work, particularly in situations where specialist expertise is limited. Our research advancements in both prostate and breast cancer were the result of collaborations with the Naval Medical Center San Diego and support from Verily. Our appreciation also goes to several institutions that provided access to de-identified data, and many pathologists who provided advice or reviewed prostate cancer samples.

Machine Learning and AI are exciting topics in science, promising faster and more accurate data analyses and new insights.