T eaching Perception Jonathan H. Connell 1 Abstract -- The visual world is very rich and generally too complex to perceive in its entirety. Y et only certain features are typically required to adequately perform some task in a given situation. Rather than hardwire-in decisions about when and what to sense, this paper describes a robotic system whose behavioral policy can be set by verbal instructions it receives. These capabilities are demonstrated in an associated video [1] showing the fully implemented system guiding the perception of a physical robot in simple scenario. The structure and functioning of the underlying natural language based symbolic reasoning system is also discussed. I. INTRODUCTION Sensing is not without costs. For any given object there are many things that can be known about it. What constitutes a reasonable amount of information to obtain? For instance, to identify an object in a scene a robot could run a DNN recognizer. But, depending on the resources available, this may take a noticeable amount of time. And, while some recognizers have Nary outputs, others are designed as one-versus-all. In this case, to classify an object a robot might have to run N separate nets.

Home robots may come with many sophisticated built-in abilities, however there will always be a degree of customization needed for each user and environment. Ideally this should be accomplished through one-shot learning, as collecting the large number of examples needed for statistical inference is tedious. A particularly appealing approach is to simply explain to the robot, via speech, what it should be doing. In this paper we describe the ALIA cognitive architecture that is able to effectively incorporate user-supplied advice and prohibitions in this manner. The functioning of the implemented system on a small robot is illustrated by an associated video [11]. 1 INTRODUCTION A typical home robot of the future might have built-in navigation, object recognition, task planning, and dexterous manipulation. Y et, despite these sophisticated capabilities, there are still things it cannot know when it first arrives. For instance, what a particular room in the house is called, even if it can identify the general type.

Scientists from Japan have used machine learning for the first time to identify a new figure among the ancient motifs of Peru's Nazca Lines. The illustration, known as a geoglyph, is thought to date to between 100 BC and 500 AD, and was made by removing the dark stones of the Nazca Desert to reveal the white sand beneath. It's small, just five meters in height, and it shows a humanoid figure grasping a cane or club. Like the other drawings in the Nazca Desert, its exact function is unknown, but its discovery next to an ancient path suggests it might have been used as a waypoint. "It is in an area that we often investigated, but we did not know the geoglyph existed," Professor Makato Sakai, the leader of a team from Yamagata University that conducted the research, told The Verge over email.

IBM power systems and Yamagata University collaborated to develop an AI-enabled cloud platform and geoscope that uncovered mysterious and ancient geoglyphs. Could robots become archaeological assistants, shuffling or trudging across sandy terrain like R2D2 and C3P0 in 1977's original " Star Wars?" Artificial Intelligence (AI) and machine-learning algorithms, along with geospatial data, are being used to uncover mysterious and ancient geoglyphs, courtesy of a collaboration between IBM power systems and Yamagata University. And, using the new AI, scientists discovered a new formation of very large geoglyphs in the soil on the Nazca Lines in southern Peru-- the first to be found using AI. While straight lines dominate the Nazca desert landscape, figurative designs of animals and plants have evolved.

The time frame for this idea is 2 decades-plus. You will get out of the box thinking from me sometimes but it comes with a connecting thread running it -- which you will profit from. The thread here will run for decades. I'm going to talk about The Future, The Fear of it and Fixing those Fears. We have worries about the future. I'm talking about how to survive the big unknown about the future: Change and its impact on our lives -- jobs, health, safety and family. There's a joke from a startup guy who said, "I sleep like a baby, I wake up crying and needing to poop every couple of hours." On the spectrum of humans worrying, there's people like Buddha on one end, who does great - living his best life in the present. Not me, (I might be in danger of looking like the Buddha with my diet.)

Located in the Nazca Desert in southern Peru, the Nazca Lines are a collection of giant etchings that only make sense from a great height. Now AI is helping speed up the hunt for more hidden symbols--and has already had some success. Mysterious sand symbols: Since their discovery in the 1920s, the Nazca Lines have continued to mystify experts. Created between 200 BCE and 600 CE, they were made by removing stones to reveal the white sand beneath and depict various geometric shapes, people, and animals, known as geoglyphs. In 1994 they were designated a UNESCO World Heritage Site, but their purpose and meaning have continued to elude historians.

This paper introduces EQShapelets (EarthQuake Shapelets) a time-series shape-based approach embedded in machine learning to autonomously detect earthquakes. It promises to overcome the challenges in the field of seismology related to automated detection and cataloging of earthquakes. EQShapelets are amplitude and phase-independent, i.e., their detection sensitivity is irrespective of the magnitude of the earthquake and the time of occurrence. They are also robust to noise and other spurious signals. The detection capability of EQShapelets is tested on one week of continuous seismic data provided by the Northern California Seismic Network (NCSN) obtained from a station in central California near the Calaveras Fault. EQShapelets combined with a Random Forest classifier, detected all of the cataloged earthquakes and 281 uncataloged events with lower false detection rate thus offering a better performance than autocorrelation and FAST algorithms. The primary advantage of EQShapelets over competing methods is the interpretability and insight it offers. Shape-based approaches are intuitive, visually meaningful and offers immediate insight into the problem domain that goes beyond their use in accurate detection. EQShapelets, if implemented at a large scale, can significantly reduce catalog completeness magnitudes and can serve as an effective tool for near real-time earthquake monitoring and cataloging.

--Global physical event detection has traditionally relied on dense coverage of physical sensors around the world; while this is an expensive undertaking, there have not been alternatives until recently. The ubiquity of social networks and human sensors in the field provides a tremendous amount of real-time, live data about true physical events from around the world. However, while such human sensor data have been exploited for retrospective large-scale event detection, such as hurricanes or earthquakes, they has been limited to no success in exploiting this rich resource for general physical event detection. Prior implementation approaches have suffered from the concept drift phenomenon, where real-world data exhibits constant, unknown, unbounded changes in its data distribution, making static machine learning models ineffective in the long term. We propose and implement an end-to-end collaborative drift adaptive system that integrates corroborative and probabilistic sources to deliver real-time predictions. Furthermore, out system is adaptive to concept drift and performs automated continuous learning to maintain high performance. We demonstrate our approach in a real-time demo available online for landslide disaster detection, with extensibility to other real-world physical events such as flooding, wildfires, hurricanes, and earthquakes. Physical event detection, such as extreme weather events or traffic accidents have long been the domain of static event processors operating on numeric sensor data or human actors manually identifying event types. However, the emergence of big data and associated data processing and analytics tools and systems have led to several applications in large-scale event and trend detection in the streaming domain [1]-[7]. However, it is important to note that many of these works are a form of retrospective analysis, as opposed to true real-time event detection, since they perform analyses on cleaned and processed data within a short-time frame in the past, with the assumption that their approaches are sustainable and will continue to function over time.

Center for Theoretical Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A. Collider data must be corrected for detector effects ("unfolded") to be compared with theoretical calculations and measurements from other experiments. Unfolding is traditionally done for individual, binned observables without including all information relevant for characterizing the detector response. We introduce OmniFold, an unfolding method that iteratively reweights a simulated dataset, using machine learning to capitalize on all available information. Our approach is un-binned, works for arbitrarily high-dimensional data, and naturally incorporates information from the full phase space. We illustrate this technique on a realistic jet substructure example from the Large Hadron Collider and compare it to standard binned unfolding methods. This new paradigm enables the simultaneous measurement of all observables, including those not yet invented at the time of the analysis.

Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper presents a deep learning framework using convolutional neural networks (CNN) and recurrent neural networks (RNN) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN model, along with other popular methods such as random forest (RF), deep fully-connected neural networks (DFNN), and LASSO, was used to forecast corn and soybean yield across the entire Corn Belt (including 13 states) in the United States for years 2016, 2017, and 2018 using historical data. The new model achieved a root-mean-square-error (RMSE) 9% and 8% of their respective average yields, substantially outperforming all other methods that were tested. The CNN-RNN have three salient features that make it a potentially useful method for other crop yield prediction studies. (1) The CNN-RNN model was designed to capture the time dependencies of environmental factors and the genetic improvement of seeds over time without having their genotype information. (2) The model demonstrated the capability to generalize the yield prediction to untested environments without significant drop in the prediction accuracy. (3) Coupled with the backpropagation method, the model could reveal the extent to which weather conditions, accuracy of weather predictions, soil conditions, and management practices were able to explain the variation in the crop yields.