Researchers at Massachusetts General Hospital (MGH) have developed a deep learning model that identifies imaging biomarkers on screening mammograms to predict a patient's risk for developing breast cancer with greater accuracy than traditional risk assessment tools. Results of the study are being presented at the annual meeting of the Radiological Society of North America (RSNA). "Traditional risk assessment models do not leverage the level of detail that is contained within a mammogram," said Leslie Lamb, M.D., M.Sc., breast radiologist at MGH. "Even the best existing traditional risk models may separate sub-groups of patients but are not as precise on the individual level." Currently available risk assessment models incorporate only a small fraction of patient data such as family history, prior breast biopsies, and hormonal and reproductive history. Only one feature from the screening mammogram itself, breast density, is incorporated into traditional models.

In late January, scientists at DeepMind, Google's London-based AI unit, gathered to discuss whether there was anything they could do to help fight the brewing coronavirus pandemic. At the time, the spread of Covid-19 was still largely confined to the city of Wuhan, but as case numbers continued to grow exponentially, machine learning experts from London to San Francisco were gearing up to try and harness the power of AI to fight the Sars-CoV-2 virus. "Our first reaction was to think how we might be able to help," says Demis Hassabis, CEO and co-founder of DeepMind. "Front of mind was our system, AlphaFold, which we had shown could predict the 3D structure of proteins with unprecedented accuracy compared to other computational methods." At the start of March, DeepMind released predictions generated by AlphaFold for the structures of various proteins associated with SARS-CoV-2, to try and accelerate the process of understanding how the virus functions.

Deep learning is one of the most advanced forms of machine learning, and is showing new developments in many industries. In this article, we'll explain the concept and give some examples of the latest and greatest ways it's being used. There have been many attempts at creating a definition of deep learning. As we've explained in the past, machine learning can be considered as a sort of offspring of artificial intelligence. In the same way, you can view deep learning as a further evaluated type of machine learning.

A Recurrent Neural Network or RNN is a popular multi-layer neural network that has been utilised by researchers for various purposes including classification and prediction. The applications of this network include speech recognition, language modelling, machine translation, handwriting recognition, among others. The recurrent neural network is an interesting topic and what's more about this article is that all the courses mentioned here are free to learn. Below here, we listed down the top 10 free resources, in no particular order, to learn recurrent neural networks (RNNs). About: Here, you will understand how to implement recurrent neural networks (RNNs).

This work proposes a spectral convolutional neural network (CNN) operating on laser induced breakdown spectroscopy (LIBS) signals to learn to (1) disentangle spectral signals from the sources of sensor uncertainty (i.e., pre-process) and (2) get qualitative and quantitative measures of chemical content of a sample given a spectral signal (i.e., calibrate). Once the spectral CNN is trained, it can accomplish either task through a single feed-forward pass, with real-time benefits and without any additional side information requirements including dark current, system response, temperature and detector-to-target range. Our experiments demonstrate that the proposed method outperforms the existing approaches used by the Mars Science Lab for pre-processing and calibration for remote sensing observations from the Mars rover, 'Curiosity'.

One crucial challenge of real-world multilingual speech recognition is the long-tailed distribution problem, where some resource-rich languages like English have abundant training data, but a long tail of low-resource languages have varying amounts of limited training data. To overcome the long-tail problem, in this paper, we propose Adapt-and-Adjust (A2), a transformer-based multi-task learning framework for end-to-end multilingual speech recognition. The A2 framework overcomes the long-tail problem via three techniques: (1) exploiting a pretrained multilingual language model (mBERT) to improve the performance of low-resource languages; (2) proposing dual adapters consisting of both language-specific and language-agnostic adaptation with minimal additional parameters; and (3) overcoming the class imbalance, either by imposing class priors in the loss during training or adjusting the logits of the softmax output during inference. Extensive experiments on the CommonVoice corpus show that A2 significantly outperforms conventional approaches.

Autoencoders are a class of artificial neural networks which have gained a lot of attention in the recent past. Using the encoder block of an autoencoder the input image can be compressed into a meaningful representation. Then a decoder is employed to reconstruct the compressed representation back to a version which looks like the input image. It has plenty of applications in the field of data compression and denoising. Another version of Autoencoders (AE) exist, called Variational AE (VAE) which acts as a generative model like GAN. Recently, an optimizer was introduced which is known as lookahead optimizer which significantly enhances the performances of Adam as well as SGD. In this paper, we implement Convolutional Autoencoders (CAE) and Convolutional Variational Autoencoders (CVAE) with lookahead optimizer (with Adam) and compare them with the Adam (only) optimizer counterparts. For this purpose, we have used a movie dataset comprising of natural images for the former case and CIFAR100 for the latter case. We show that lookahead optimizer (with Adam) improves the performance of CAEs for reconstruction of natural images.

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems (ITS), in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular ITS research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

Domain adaptation, as a task of reducing the annotation cost in a target domain by exploiting the existing labeled data in an auxiliary source domain, has received a lot of attention in the research community. However, the standard domain adaptation has assumed perfectly observed data in both domains, while in real world applications the existence of missing data can be prevalent. In this paper, we tackle a more challenging domain adaptation scenario where one has an incomplete target domain with partially observed data. We propose an Incomplete Data Imputation based Adversarial Network (IDIAN) model to address this new domain adaptation challenge. In the proposed model, we design a data imputation module to fill the missing feature values based on the partial observations in the target domain, while aligning the two domains via deep adversarial adaption. We conduct experiments on both cross-domain benchmark tasks and a real world adaptation task with imperfect target domains. The experimental results demonstrate the effectiveness of the proposed method.

Model compression is a ubiquitous tool that brings the power of modern deep learning to edge devices with power and latency constraints. The goal of model compression is to take a large reference neural network and output a smaller and less expensive compressed network that is functionally equivalent to the reference. Compression typically involves pruning and/or quantization, followed by re-training to maintain the reference accuracy. However, it has been observed that compression can lead to a considerable mismatch in the labels produced by the reference and the compressed models, resulting in bias and unreliability. To combat this, we present a framework that uses a teacher-student learning paradigm to better preserve labels. We investigate the role of additional terms to the loss function and show how to automatically tune the associated parameters. We demonstrate the effectiveness of our approach both quantitatively and qualitatively on multiple compression schemes and accuracy recovery algorithms using a set of 8 different real-world network architectures. We obtain a significant reduction of up to 4.1X in the number of mismatches between the compressed and reference models, and up to 5.7X in cases where the reference model makes the correct prediction.