AI Technology & Industry Review
Hosted annually in the United States, the Computer Vision and Pattern Recognition Conference received 2,620 submissions, accepted 783 papers, attracted 127 sponsors with $859,000 in sponsorship and close to 5,000 attendees.
PixelGAN is an autoencoder for which the generative path is a convolutional autoregressive neural network on pixels, conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.
We explore top-notch Swiss AI facilities: starting with deep learning and neural network research at IDSIA in Lugano, to interdisciplinary research at École Polytechnique Fédérale de Lausanne and University of Basel, and ending with robotics innovations at ETH in Zurich and University of Zurich.
This paper presents a deep learning architecture to map the vehicle detection in the frontal view onto a bird’s eye view of the road scene, while preserving the size and direction of the moving vehicle.
Most categories have been taken over by e-commerce yet the category of fresh groceries hasn’t been disrupted by online.
This paper demonstrates a framework called Mixture Of Distribution Language Models (MODLMs), which provides a single mathematical framework that encompasses several widely used classes of LMs.
Computer science and machine learning scholars are increasingly interested in languages, and natural language processing has shown great progress as a result.
Minimization of the KL-divergence can be thought of as maximizing the likelihood ratio, which appears in numerous applications.
Apple is confused about what its next big thing will be.
One crucial standard in measuring autonomous vehicles is whether the autonomous vehicles can go through intersections with no signals. In this paper, the authors provide us with a new strategy of using Deep Reinforcement Learning.
In his blog post “How Data Science Apply to Robotics” on Data Science Central, Dr. Ammar A. Raja points out that there are two major problems scientists have encountered while applying data science to robotics.
Bayes’ Theorem is useful for dealing with conditional probabilities, since it provides a way for us to reverse them.
By accurately predicting the category of an email, we can better extract useful information from it according to its corresponding templates.
Curiosity is related to the field of intrinsic motivation, and is recognized as a factor in a wide range of human endeavour.
Although no innovations for the NMT architecture was introduced, the authors claim that a classic NMT baseline system with carefully tuned hyperparameters can still achieve comparable result to the state-of-the-art.
From LSTM deep learning technique to self-learning humanoid robot, Jürgen Schmidhuber’s research teams have won awards in various machine learning competitions, including medical image recognition.
Instead of exploring target-side monolingual data for NMT, the author of this paper proposes two novel methods for source-side monolingual data exploration.
“To pretend science is morally neutral, and that you can develop anything and have clean hands because it is someone else using it to kill people is extremely naive, and scientists should know that.” – UC Berkeley’s Dr. Stuart Russell
The rubber on GelSight sensor will conform to any object pressed against it, resulting in the reflective lights on the metallic paint to vary according to different materials and shapes.
Multimodal convolutional neural networks for appearance-based gaze estimation that significantly outperforms state-of-the-art methods in the most challenging cross-dataset evaluation
Instead of investigating what steps the brain takes to process information, the authors of this paper link brain activity directly to the learning process.
Gary Marcus the Professor of Psychology at New York University, CEO and Founder of Geometric Intelligence, speaks at GMIS 2017.