Since its invention in the 1970s, magnetic resonance imaging (MRI) has opened up a window onto the world beneath our skin. By exploiting the way the nuclei of hydrogen atoms in water and fat molecules resonate in a strong magnetic field, MRI can generate high-contrast three-dimensional images of soft body tissues, joints, and bones. MRI allows clinicians to see evidence of injury and disease within the body, ranging from torn muscle to damaged cartilage, ligaments, and tendons, as well as tumors or other disease lesions within major organs, and blood-flow blockages in the brain, all without the ionizing radiation of the X-rays used in computed tomography (CT) scans. There is, however, a considerable usability problem with the MRI scanner as we currently know it: the technology takes far too long to acquire images, forcing patients to lie still in the confined maw of a massive magnet for up to an hour. With the observable world reduced to a halo of grayish plastic just inches from one's nose, it is a particularly tough experience for those suffering from claustrophobia.

Momenta is now the recipient of a $500 million investment round led by Toyota in order to provide new technologies like automated HD mapping and updates through vision-based technologies, a company announcement says. Both companies are looking to promote their new Toyota Automated Mapping platform for Chinese customers. Momenta specializes in vision-based, or camera-based, HD mapping, which utilizes camera, GPS and IMU to automatically generate HD maps. The maps are of a high quality through cutting-edge technologies like "deep-learning based perception, SLAM (simultaneous localization and mapping), etc.," and come with rich geometry features like traffic signs, poles, lane borders, traffic lights and road markings. In addition, the tech generates road-level and lane topology and semantic features.

Nintendo's next Switch may use an NVIDIA GPU that supports Deep Learning Super Sampling (DLSS) that will allow it to output higher-quality graphics, Bloomberg has reported. The new system-on-chip would enable output at up to 4K quality when the Switch is connected to a TV, and will also reportedly include an upgraded CPU and increased memory. The next-gen Switch is set to have a built-in 7-inch 720p OLED display and 4K output, according to a previous Bloomberg report. Since NVIDIA's DLSS allows for good-quality 4K upscaling, it's not clear if an upgraded NVIDIA GPU would support native 4K or for upscale from a lower resolution. The current generation of Switch uses NVIDIA's Tegra graphics to output up to 1080p game quality.

Although the potential for artificial intelligence to transform healthcare in lower income countries has been much hyped, the technology is proving genuinely useful in helping Africa overcome difficulties in tackling diseases. Such technology can automate medical tasks and help doctors to do more with limited resources. It can even accelerate advances if certain barriers are overcome. The work of minoHealth AI Labs, the Ghana-based data science start-up that I founded, offers one example. By collecting medical images, we are seeking to automate radiology through the use of deep learning.

We are teaching a major update of the course Spring 2021 as an official UC Berkeley course and as an online course, with all lectures and labs available for free. There are many great courses to learn how to train deep neural networks. However, training the model is just one part of shipping a deep learning project. The course is aimed at people who already know the basics of deep learning and want to understand the rest of the process of creating production deep learning systems. While we cover the basics of deep learning (backpropagation, convolutional neural networks, recurrent neural networks, transformers, etc), we expect these lectures to be mostly review.

The week of February 15, we cover RNNs and applications in Natural Language Processing, and start doing sequence processing in lab.

In this section we will learn - What does Machine Learning mean. What are the meanings or different terms associated with machine learning? You will see some examples so that you understand what machine learning actually is. It also contains steps involved in building a machine learning model, not just linear models, any machine learning model.

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on its performance on a set of training problems. This data-driven procedure generates methods that can efficiently solve problems similar to those in the training. In sharp contrast, the typical and traditional designs of optimization methods are theory-driven, so they obtain performance guarantees over the classes of problems specified by the theory. The difference makes L2O suitable for repeatedly solving a certain type of optimization problems over a specific distribution of data, while it typically fails on out-of-distribution problems. The practicality of L2O depends on the type of target optimization, the chosen architecture of the method to learn, and the training procedure. This new paradigm has motivated a community of researchers to explore L2O and report their findings. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization. We set up taxonomies, categorize existing works and research directions, present insights, and identify open challenges.

Robot learning is often simplified to planar manipulation due to its data consumption. Then, a common approach is to use a fully-convolutional neural network to estimate the reward of grasp primitives. In this work, we extend this approach by parametrizing the two remaining, lateral Degrees of Freedom (DoFs) of the primitives. We apply this principle to the task of 6 DoF bin picking: We introduce a model-based controller to calculate angles that avoid collisions, maximize the grasp quality while keeping the uncertainty small. As the controller is integrated into the training, our hybrid approach is able to learn about and exploit the model-based controller. After real-world training of 27000 grasp attempts, the robot is able to grasp known objects with a success rate of over 92% in dense clutter. Grasp inference takes less than 50ms. In further real-world experiments, we evaluate grasp rates in a range of scenarios including its ability to generalize to unknown objects. We show that the system is able to avoid collisions, enabling grasps that would not be possible without primitive adaption.

The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fault localization to find potentially faulty network parameters (such as the weights) and then performs repair using constraint solving to apply small modifications to the parameters to remedy the defects. We present novel strategies to enable precise yet efficient repair such as inferring correctness specifications to act as oracles for intermediate layer repair, and generation of experts for each class. We demonstrate the technique in the context of three different scenarios: (1) Improving the overall accuracy of a model, (2) Fixing security vulnerabilities caused by poisoning of training data and (3) Improving the robustness of the network against adversarial attacks. Our evaluation on MNIST and CIFAR-10 models shows that NNrepair can improve the accuracy by 45.56 percentage points on poisoned data and 10.40 percentage points on adversarial data. NNrepair also provides small improvement in the overall accuracy of models, without requiring new data or re-training.