Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy pruning method which we call Fisher pruning. Through a combination of knowledge distillation and Fisher pruning, we obtain much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the CAT2000 dataset. Speeding up single-image gaze prediction is important for many real-world applications, but it is also a crucial step in the development of video saliency models, where the amount of data to be processed is substantially larger.

We propose a method (TT-GP) for approximate inference in Gaussian Process (GP) models. We build on previous scalable GP research including stochastic variational inference based on inducing inputs, kernel interpolation, and structure exploiting algebra. The key idea of our method is to use Tensor Train decomposition for variational parameters, which allows us to train GPs with billions of inducing inputs and achieve state-of-the-art results on several benchmarks. Further, our approach allows for training kernels based on deep neural networks without any modifications to the underlying GP model. A neural network learns a multidimensional embedding for the data, which is used by the GP to make the final prediction. We train GP and neural network parameters end-to-end without pretraining, through maximization of GP marginal likelihood. We show the efficiency of the proposed approach on several regression and classification benchmark datasets including MNIST, CIFAR-10, and Airline.

We develop a new approach to learn the parameters of regression models with hidden variables. In a nutshell, we estimate the gradient of the regression function at a set of random points, and cluster the estimated gradients. The centers of the clusters are used as estimates for the parameters of hidden units. We justify this approach by studying a toy model, whereby the regression function is a linear combination of sigmoids. We prove that indeed the estimated gradients concentrate around the parameter vectors of the hidden units, and provide non-asymptotic bounds on the number of required samples. To the best of our knowledge, no comparable guarantees have been proven for linear combinations of sigmoids.

Brace yourself, Artificial Intelligence is becoming more powerful by the minute. According to a study by researchers from Japan, Artificial Intelligence is one step closer to mind reading machines illustrated in popular science fiction films. Scientists have recently created a set of'deep learning' algorithm, modeled on the human brain which can, eventually, be used to decipher the human brain. Japanese scientists have developed an algorithm that can read human thoughts with a disturbing accuracy, according to details from a recently published study available on bioRxiv. Other than the fact that we'll soon have AI running around reading your mind (joking), is that it isn't the first time its been done.

This is the Udacity's Self-Driving Car Engineer Nanodegree Program final project for the 1st Term. To write a software pipeline to identify vehicles in a video from a front-facing camera on a car. In my implementation, I used a Deep Learning approach to image recognition. Specifically, I leveraged the extraordinary power of Convolutional Neural Networks (CNNs) to recognize images. However, the task at hand is not just to detect a vehicle's presence, but rather to point to its location. It turns out CNNs are suitable for these type of problems as well.

This is part two of my deep learning solution for lane detection, which covers the actual models I created in finding my final approach to the problem, as well as some potential improvements. Be sure to read Part One for the limitations of my previous approaches as well as the preliminary data used prior to the changes I made below. The code and data mentioned here and in the earlier post can be found in my Github repo. With a decent dataset created, I was ready to make my first model for using deep learning to detect lane lines. You may be asking, "Wait, I thought you were trying to get rid of perspective transformation?"

With all the hype surrounding artificial intelligence, you would be forgiven for thinking that developing the algorithms powering deep learning are where the toughest challenges in the industry are.

Deep Learning ultimately is about finding a minimum that generalizes well -- with bonus points for finding one fast and reliably. Our workhorse, stochastic gradient descent (SGD), is a 60-year old algorithm (Robbins and Monro, 1951) [1], that is as essential to the current generation of Deep Learning algorithms as back-propagation. Different optimization algorithms have been proposed in recent years, which use different equations to update a model's parameters. Adam (Kingma and Ba, 2015) [18] was introduced in 2015 and is arguably today still the most commonly used one of these algorithms. This indicates that from the Machine Learning practitioner's perspective, best practices for optimization for Deep Learning have largely remained the same.

The release goes on, "NVIDIA DRIVE provides a holistic safety platform that includes process, technologies and simulation systems, as described below: (1) Process: Sets out the steps for establishing a pervasive safety methodology for the design, management and documentation of the self-driving system. These include NVIDIA-designed IP related to NVIDIA Xavier covering CPU and GPU processors, deep learning accelerator, image processing ISP, computer vision PVA, and video processors – all at the highest quality and safety standards. Included are lockstep processing and error-correcting code on memory and buses, with built-in testing capabilities. The ASIL-C NVIDIA DRIVE Xavier processor and ASIL-D rated safety microcontroller with appropriate safety logic can achieve the highest system ASIL-D rating."

OpenAI, a $1 billion (£687 million) artificial intelligence company backed by Elon Musk, has built a "gym" where developers can train their AI systems to get smarter. Using OpenAI's open source toolkit, available for download now, developers can access "environments" where they can test their AI bots. The OpenAI Gym, currently in beta, provides a number of environments, including more than 50 Atari games, such as "Space Invaders," "Pong," "Asteroids" and "Pac-Man". Developers can also test their AIs on board games like Go, which was recently mastered by an agent built by London startup Google DeepMind. "Over time, we plan to greatly expand this collection of environments," wrote OpenAI's Greg Brockman and John Schulman in a blog post.