AI for Earth puts Microsoft's cloud and AI tools in the hands of those working to solve global environmental challenges. Land cover mapping is part of Microsoft's AI for Earth program, which was created in order to fundamentally change the way that society monitors, models, and ultimately manages Earth's natural resources. To power the land cover mapping work, DNNs are used to perform land use classification using tens of terabytes of high-resolution satellite images from National Agriculture Imagery Program (NAIP). However, Deep Neural Networks (DNNs) are challenging to infer cost-effectively, and deploy in large-scale online services with low latencies and price/performance. Microsoft Project Brainwave is a hardware architecture designed to enable high performance real-time AI computations, and the architecture is deployed on field programmable arrays (FPGAs). This wave of hardware innovation will fundamentally transform latencies and price-performance for large scale use of DNNs. In this session, we will walkthrough how FPGAs are used within Microsoft, and how we can tap the power of FPGAs for real-time AI. We will share the secrets of how we are able to perform land cover classification on 20 terabytes of high-resolutions satellite images from NAIP in ten minutes, at the rate of over 415,000 inferences/second.

Several exciting trends are driving the birth of the intelligent cloud. The vast majority of world's data is now connected data resident in the cloud. The majority of world's new software is now connected software, also resident in or using the cloud. New cloud based Machine Learning as a Service platforms help transform data into intelligence and build cloud-hosted intelligent APIs for connected software applications. Face analysis, computer vision, text analysis, speech recognition, and more traditional analytics such as churn prediction, recommendations, anomaly detection, forecasting, and clustering are all available now as cloud APIs, and far more are being created at a rapid pace. Cloud hosted marketplaces for crowdsourcing intelligent APIs have been launched. In this talk I will review what these trends mean for the future of data science and show examples of revolutionary applications that you can build using cloud platforms.

This article presents a self-organizing neural network model for the simultaneous and cooperative development of topographic receptive fields and lateral interactions in cortical maps. Both afferent and lateral connections adapt by the same Hebbian mechanism in a purely local and unsupervised learning process. Afferent input weights of each neuron self-organize into hill-shaped profiles, receptive fields organize topographically across the network, and unique lateral interaction profiles develop for each neuron. The model demonstrates how patterned lateral connections developed based on correlated activity and explains why lateral connection patterns closely follow receptive field properties such as ocular dominance.

A neural network model for the self-organization of ocular dominance and lateral connections from binocular input is presented. The self-organizing process results in a network where (1) afferent weights of each neuron or(cid:173) ganize into smooth hill-shaped receptive fields primarily on one of the reti(cid:173) nas, (2) neurons with common eye preference form connected, intertwined patches, and (3) lateral connections primarily link regions of the same eye preference. Similar self-organization of cortical structures has been ob(cid:173) served experimentally in strabismic kittens. The model shows how pat(cid:173) terned lateral connections in the cortex may develop based on correlated activity and explains why lateral connection patterns follow receptive field properties such as ocular dominance.