Following his graduation from Stanford University with a B.S. in Mathematics and an M.S. in Computer Science, Lukas led the Search Relevance Team for Yahoo! He then worked as a senior data scientist at Powerset, which was acquired by Microsoft in 2008.

Disruptive technologies like Artificial Intelligence (AI) and Internet of Things (IoT) will enable organisations to deliver a million midday meals to school children in India, said a top official of software major Accenture on Thursday. "We have applied AI, IoT and block-chain to exponentially increase the number of midday meals served to children in state-run schools under'Million Meals' project with NGO Akshaya Patra," said Accenture Labs Managing Director Sanjay Podder in a statement here. Block-chain is a distributed database that compiles a growing list of ordered records called blocks. The US-based Accenture collaborated with the city-based Akshaya Patra Foundation, which operates the government-funded MidDay Meal Scheme in state-run and state-aided schools, in implementing the novel project with new IT products and solutions. "The project has also demonstrated how new technologies can help address challenges in mass meal production and delivery by revolutionising supply chain and operations," asserted Podder.

We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we extend an approach taken by the "Whitened neural networks" model. We make the whitening process not only in feed-forward direction as in the original model, but also in the back-propagation phase. Its efficacy is shown by an application of this "Bidirectional whitened neural networks" model to a handwritten character recognition data (MNIST data).

The multivariate linear regression model with shuffled data and additive Gaussian noise arises in various correspondence estimation and matching problems. Focusing on the denoising aspect of this problem, we provide a characterization the minimax error rate that is sharp up to logarithmic factors. We also analyze the performance of two versions of a computationally efficient estimator, and establish their consistency for a large range of input parameters. Finally, we provide an exact algorithm for the noiseless problem and demonstrate its performance on an image point-cloud matching task. Our analysis also extends to datasets with outliers.

We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and prediction models on fully labeled training data by means of a bottom-up strategy. Our novel bottom-up method is a recursive scheme whereby a high-accuracy complex model is first trained. Then a low-complexity gating and prediction model are subsequently learnt to adaptively approximate the high-accuracy model in regions where low-cost models are capable of making highly accurate predictions. We pose an empirical loss minimization problem with cost constraints to jointly train gating and prediction models. On a number of benchmark datasets our method outperforms state-of-the-art achieving higher accuracy for the same cost.

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us to identify spatio-temporal abstractions directly from features and may be used as a sub-goal detector in future work. Using our tools we reveal that the features learned by DQNs aggregate the state space in a hierarchical fashion, explaining its success. Moreover, we are able to understand and describe the policies learned by DQNs for three different Atari2600 games and suggest ways to interpret, debug and optimize deep neural networks in reinforcement learning.

When Sahil Singla joined the social impact startup Farmguide, he was shocked to discover that thousands of rural farmers in India commit suicide every year. When harvests go awry, desperate farmers are forced to borrow from microfinance loan sharks at crippling rates. Unable to pay back these predatory loans, victims kill themselves – often by grisly methods like swallowing pesticides – to escape the threats and violence of their ruthless debt collectors. Singla and his team are tackling this social injustice with one unexpected but powerful tool: deep learning. Recent growth of computational power and structured data sets has allowed deep learning algorithms to achieve extraordinary results.

Since Facebook introduced chatbots to its messaging platform last year, there's been widespread enthusiasm for bots that schedule flights, book hotel rooms or order Ubers for you -- this in the same app that you use to chat with your friends. Chatbots and AI have been around for a while (look at what China's leading messaging app WeChat has accomplished) but the fact that Facebook chose to launch this feature recently could mean that this technology is finally mature enough for mainstream adoption, at least in the Western world. With things changing so fast in the tech scene and designers struggling to stay informed on the latest trends, I was absolutely delighted to see a hackathon for chatbots on Eventbrite. What better way to learn about chatbots and AI than to mingle with developers and build one? Most developers at the event used Recime to set up their bots.

HOUSTON -- (April 17) -- Rice University computer scientists are mapping a new solution for interior navigational location detection by linking it to existing sensors in mobile devices. Their results were presented in a paper at last month's 2017 Design, Automation and Test in Europe (DATE) Conference in Lausanne, Switzerland. Rice University researchers (from left) Chen Luo, Anshumali Shrivastava and Juan Jose Gonzalez Espana published a paper on location detection for navigation with Krishna Palem (not pictured). Six months ago, the same researchers published a paper on their first technology for a new indoor mobile positioning system called CaPSuLe. The navigational location detection system began as a solution for mobile device users inside large indoor spaces like office complexes or shopping malls where GPS navigation falters under poor signals that quickly deplete battery life.