I will present three recent projects within the 3D Deep Learning research line from my team at Google Research: (1) a deep network for reconstructing the 3D shape of multiple objects appearing in a single RGB image (ECCV'20). (2) a new conditioning scheme for normalizing flow models. It enables several applications such as reconstructing an object's 3D point cloud from an image, or the converse problem of rendering an image given a 3D point cloud, both within the same modeling framework (CVPR'20); (3) a neural rendering framework that maps a voxelized object into a high quality image. It renders highly-textured objects and illumination effects such as reflections and shadows realistically. It allows controllable rendering: geometric and appearance modifications in the input are accurately represented in the final rendering (CVPR'20).
Game Development requires a vast array of tools, techniques, and expertise, ranging from game design, artistic content creation, to data management and low level engine programming. Yet all of these domains have one kind of task in common - the transformation of one kind of data into another. Meanwhile, advances in Machine Learning have resulted in a fundamental change in how we think about these kinds of data transformations - allowing for accurate and scalable function approximation, and the ability to train such approximations on virtually unlimited amounts of data. In this talk I will present how these two fundamental changes in Computer Science affect game development - how they can be used to improve game technology as well as the way games are built - and the exciting new possibilities and challenges they bring along the way.
Organizers: Abhinanda Ranjit Punnakkal
Since the release of the Kinect, RGB-D cameras have been used in several consumer devices, including smartphones. In this talk, I will present two challenging uses of this technology. With multiple RGB-D cameras, it is possible to reconstruct a 3D scene and visualize it from any point of view. In the first part of the talk, I will show how such a scene can be streamed and rendered as a point cloud in a compelling way and its appearance improved by the use of external cinema cameras. In the second part of the talk, I will present my work on how an RGB-D camera can be used for enabling real-walking in virtual reality by making the user aware of the surrounding obstacles. I present a pipeline to create an occupancy map from a point cloud on the fly on a mobile phone used as a virtual reality headset. This occupancy map can then be used to prevent the user from hitting physical obstacles when walking in the virtual scene.
Organizers: Sergi Pujades
I’ll start with a concept of 1990 that has become popular: unsupervised learning without a teacher through two adversarial neural networks (NNs) that duel in a minimax game, where one NN minimizes the objective function maximized by the other. The first NN generates data through its output actions, the second NN predicts the data. The second NN minimizes its error, thus becoming a better predictor. But it is a zero sum game: the first NN tries to find actions that maximize the error of the second NN. The system exhibits what I called “artificial curiosity” because the first NN is motivated to invent actions that yield data that the second NN still finds surprising, until the data becomes familiar and eventually boring. A similar adversarial zero sum game was used for another unsupervised method called "predictability minimization," where two NNs fight each other to discover a disentangled code of the incoming data (since 1991), remarkably similar to codes found in biological brains. I’ll also discuss passive unsupervised learning through predictive coding of an agent’s observation stream (since 1991) to overcome the fundamental deep learning problem through data compression. I’ll offer thoughts as to why most current commercial applications don’t use unsupervised learning, and whether that will change in the future.
Organizers: Bernhard Schölkopf
Insect chemical ecology is a mature, long standing field, with its own journal. By contrast, insect physical ecology is much less studied and the worked scattered. Using work done in my group, I will highlight locomotion, both in granular materials like sand and at the water surface as well as sensing, in particular olfaction and flow sensing. The bio-inspired implementations in MEMS technologies will be the closing chapter.
Organizers: Metin Sitti
In an effort to improve the performance of deep neural networks in data-scarce, non-i.i.d., or unsupervised settings, much recent research has been devoted to encoding invariance under symmetry transformations into neural network architectures. We treat the neural network input and output as random variables, and consider group invariance from the perspective of probabilistic symmetry. Drawing on tools from probability and statistics, we establish a link between functional and probabilistic symmetry, and obtain functional representations of probability distributions that are invariant or equivariant under the action of a compact group. Those representations characterize the structure of neural networks that can be used to represent such distributions and yield a general program for constructing invariant stochastic or deterministic neural networks. We develop the details of the general program for exchangeable sequences and arrays, recovering a number of recent examples as special cases. This is work in collaboration with Yee Whye Teh. https://arxiv.org/abs/1901.06082
Organizers: Isabel Valera
Learning new control strategies for (possibly unknown) dynamical systems is a challenging task. Reinforcement learning algorithms typically require 'fresh' data regularly, but obtaining data safely and in sufficient quantities is a challenge on real systems. Thus, it is no surprise that most recent successes have been in domains where massive amounts of data can easily be generated in simulation (e.g., games such as Atari and Go).
The molecular connectivity between genes and proteins inside a cell shows a good degree of resemblance with complex electrical circuits. This inspires the possibility of engineering a cell similar to an engineering device by plugging in genetic logic circuits. This approach, which is loosely defined as synthetic biology is an emerging field of bioengineering, where scientist use electrical and computer engineering principle to re-program cellular functions with a potential to solve next generation challenges in medicine, materials, energy, and space travel. In this talk, we discuss our efforts to create artificial and complex chemical signal processing systems using genetic logic circuits and its applications in building a technology platform for microbial robotics. We further discuss our systems biology effort to understand the effect of microgravity on human and bacterial cells during space travel.
Organizers: Metin Sitti
Neurological disorders and injuries lead to a loss of sensorimotor function in the central nervous system, which controls the musculoskeletal system. Novel systems and control methods can be employed to create neuroprostheses that restore these functions to an unprecedented degree by two major advances: (1) Long standing limitations of inertial motion tracking are overcome by novel parameter estimation and sensor fusion methods. (2) A recent extension of classic learning control methods facilitates real-time pattern adaptation in artificial muscle recruitment. We review the role of these methods in the development of biomimetic neuroprostheses and discuss their potential impact in a range of further application systems including autonomous vehicles, robotics, and multi-agent networks.
Organizers: Sebastian Trimpe
First, a short analysis of the key components of my participation in SemEval 2018, an emotion analysis contest from tweets. Namely, a transfer learning approach used for emotion classification and a context-aware attention mechanism. In my second paper, I explore how brain information can improve word representations. Neural activation models that have been proposed in the literature use a set of example words for which fMRI measurements are available in order to find a mapping between word semantics and localized neural activations. I use such models to predict neural activations on a full word lexicon. Then, I propose a cognitive computational model that estimates semantic similarity in the neural activation space and investigates the relative performance of this model for various natural language processing tasks. Finally, in my most recent work I explore cross-topic word representations. In traditional Distributional Semantic Models -like word2vec- the multiple senses of a polysemous word are conflated into a single vector space representation. In my work, I propose a DSM that learns multiple distributional representations of a word based on different topics. Moreover, we project the different topic representations in a common space and apply a smoothing technique to group redundant topic vectors.
Organizers: Soubhik Sanyal
Since Hubel and Wiesel's seminal findings in the primary visual cortex (V1) more than 50 years ago, progress in vision science has been very limited along previous frameworks and schools of thoughts on understanding vision. Have we been asking the right questions? I will show observations motivating the new path. First, a drastic information bottleneck forces the brain to process only a tiny fraction of the massive visual input information; this selection is called the attentional selection, how to select this tiny fraction is critical. Second, a large body of evidence has been accumulating to suggest that the primary visual cortex (V1) is where this selection starts, suggesting that the visual cortical areas along the visual pathway beyond V1 must be investigated in light of this selection in V1. Placing attentional selection as the center stage, a new path to understanding vision is proposed (articulated in my book "Understanding vision: theory, models, and data", Oxford University Press 2014). I will show a first example of using this new path, which aims to ask new questions and make fresh progresses. I will relate our insights to artificial vision systems to discuss issues like top-down feedbacks in hierachical processing, analysis-by-synthesis, and image understanding.