Collaborating Authors

Neural Networks

Google proposes new method to derive analytical expressions for terms in quantum mechanics…


It's no news that the giant Alphabet invests quite a lot in ML applications to science, through channels such as Google Research and Deepmind. While in the fields of chemistry and biology AlphaFold is by far its most famous project, Deepmind has also gone into quantum mechanical (QM) calculations (my blog entry here), and so is doing Google Research. QM calculations are very important in chemistry, as they provide the highest level of detail about electron densities, distributions, and spin states in molecules and materials, all the key elements required to model, understand, and predict their chemical reactivity and physicochemical properties -none of which are approachable with classical methods. The new work I comment on here comes from Google Research and also addresses ways to improve QM calculations. Specifically, Ma et al developed a new method to derive symbolic, analytical forms of DFT functionals.

OpenAI spent $160,000 on Upwork for Minecraft gamers to train a neural net


The computer program achieved the feat in ten minutes, half the time it would take a proficient human player to do it. How important might it be to master the "diamond tool" in Minecraft? Important enough to spend $160,000, according to OpenAI, the artificial intelligence startup. That is the amount of money that a team at OpenAI spent to hire players of Minecraft on the online job listings platform Upwork to submit videos of themselves playing the game. In a paper unveiled this week, "Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos," OpenAI researchers Bowen Baker and team break ground in the use of large datasets to train a neural network to mimic human keystrokes to solve different tasks in the video game.

Yann LeCun has a bold new vision for the future of AI


The centerpiece of the new approach is a neural network that can learn to view the world at different levels of detail. Ditching the need for pixel-perfect predictions, this network would focus only on those features in a scene that are relevant for the task at hand. LeCun pairs this core network with another, called the configurator, which determines what level of detail is required and tweaks the overall system accordingly. For LeCun, AGI is going to be a part of how we interact with future tech. His vision is colored by that of his employer, Meta, which is pushing a virtual-reality metaverse.

A new generative adversarial network for medical images super resolution - Scientific Reports


For medical image analysis, there is always an immense need for rich details in an image. Typically, the diagnosis will be served best if the fine details in the image are retained and the image is available in high resolution. In medical imaging, acquiring high-resolution images is challenging and costly as it requires sophisticated and expensive instruments, trained human resources, and often causes operation delays. Deep learning based super resolution techniques can help us to extract rich details from a low-resolution image acquired using the existing devices. In this paper, we propose a new Generative Adversarial Network (GAN) based architecture for medical images, which maps low-resolution medical images to high-resolution images. The proposed architecture is divided into three steps. In the first step, we use a multi-path architecture to extract shallow features on multiple scales instead of single scale. In the second step, we use a ResNet34 architecture to extract deep features and upscale the features map by a factor of two. In the third step, we extract features of the upscaled version of the image using a residual connection-based mini-CNN and again upscale the feature map by a factor of two. The progressive upscaling overcomes the limitation for previous methods in generating true colors. Finally, we use a reconstruction convolutional layer to map back the upscaled features to a high-resolution image. Our addition of an extra loss term helps in overcoming large errors, thus, generating more realistic and smooth images. We evaluate the proposed architecture on four different medical image modalities: (1) the DRIVE and STARE datasets of retinal fundoscopy images, (2) the BraTS dataset of brain MRI, (3) the ISIC skin cancer dataset of dermoscopy images, and (4) the CAMUS dataset of cardiac ultrasound images. The proposed architecture achieves superior accuracy compared to other state-of-the-art super-resolution architectures.

Deep attentive variational inference


Figure 1: Overview of a local variational layer (left) and an attentive variational layer (right) proposed in this post. Attention blocks in the variational layer are responsible for capturing long-range statistical dependencies in the latent space of the hierarchy. Generative models are a class of machine learning models that are able to generate novel data samples such as fictional celebrity faces, digital artwork, and scenic images. Currently, the most powerful generative models are deep probabilistic models. This class of models uses deep neural networks to express statistical hypotheses about the data generation process, and combine them with latent variable models to augment the set of observed data with latent (unobserved) information in order to better characterize the procedure that generates the data of interest.

12 Best Deep Learning Courses on Coursera


This is another specialization program offered by Coursera. This specialization program is for both computer science professionals and healthcare professionals. In this specialization program, you will learn how to identify the healthcare professional's problems that can be solved by machine learning. You will also learn the fundamentals of the U.S. healthcare system, the framework for successful and ethical medical data mining, the fundamentals of machine learning as it applies to medicine and healthcare, and much more. This specialization program has 5 courses. Let's see the details of the courses-

DeepMind Boosts RL Agents' Retrieval Capability to Tens of Millions of Pieces of Information


The conventional approach for improving the decision-making of deep reinforcement learning (RL) agents is to gradually amortize the useful information they gain from their experiences via gradient descent on training losses. This method however requires building increasingly large models to deal with increasingly complex environments and is difficult to adapt to novel situations. Although adding information sources can benefit agent performance, there is currently no end-to-end solution for enabling agents to attend to information outside their working memory to inform their actions. In the new paper Large-Scale Retrieval for Reinforcement Learning, a DeepMind research team introduces a novel approach that dramatically expands the information accessible to reinforcement learning (RL) agents, enabling them to attend to tens of millions of information pieces, incorporate new information without retraining, and learn in an end-to-end manner how to use this information in their decision making. In the work, the team trains a semiparametric model-based agent to predict future policies and values conditioned on future actions in a given state and adds a retrieval mechanism to enable the model to draw from information in a large-scale dataset to inform its predictions.

Portraits of the Ordinary Undead - Collection


Portraits of the Ordinary Undead is a collection that features Deep Learning generated Portraits art. What you and i will see will if the undeads will to rule the world.

La veille de la cybersécurité


Though marketers are still in the early stages of experimenting with deepfakes and deepfake technology, these videos convey a more immersive marketing experience through storytelling. Deepfake technology is a type of "deep learning." Deep learning is a machine learning type that allows computers to learn tasks independently without being explicitly programmed. Deepfake technology also involves computer vision, allowing computers to recognize objects in images. For example, computer vision uses deep learning algorithms to identify objects in photos or videos.

The Pros and Cons of Deep Learning vs. Machine Learning


Deep learning and machine learning are both important methods for analyzing data and making predictions. Each has its own advantages and disadvantages.