### Machine Learning

#### SLAM: Bringing art to life through technology

SLAM: Bringing art to life through technology by Kelly Berschauer

#### Instacart Market Basket Analysis, Winner’s Interview: 2nd place, Kazuki Onodera

Our recent Instacart Market Basket Analysis competition challenged Kagglers to predict which grocery products an Instacart consumer will purchase again and when. Imagine, for example, having milk ready to be added to your cart right when you run out, or knowing that it’s time to stock up agai…

#### Using social media data to help measure smoke exposure

When natural disasters strike, people turn to Facebook to understand what’s happening and to share important safety information. The same […] Using social media data to help measure smoke exposure by Kelly Berschauer

#### New leadership for MIT-IBM Watson AI Lab

Computer vision and machine learning expert Antonio Torralba to lead new artificial intelligence research lab. New leadership for MIT-IBM Watson AI Lab by School of Engineering

#### Data Notes: Back to school tutorial Kernels + Datasets Awards

For many Kagglers, the academic year is getting started which means brushing up on coding skills, learning new machine learning techniques, and finding the right datasets for class projects. In this month’s Data Notes, we highlight new features like tagging and our pro-tips for finding datase…

#### Text Compression for Sentiment Analysis via Evolutionary Algorithms

Can textual data be compressed intelligently without losing accuracy in evaluating sentiment? In this study, we propose a novel evolutionary compression algorithm, PARSEC (PARts-of-Speech for sEntiment Compression), which makes use of Parts-of-Speech tags to compress text in a way that sacrifices m…

#### Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring increasingly longer training as problems become mo…

#### Jointly Optimizing Placement and Inference for Beacon-based Localization

The ability of robots to estimate their location is crucial for a wide variety of autonomous operations. In settings where GPS is unavailable, measurements of transmissions from fixed beacons provide an effective means of estimating a robot’s location as it navigates. The accuracy of such a b…

#### Spatial features of synaptic adaptation affecting learning performance

Recent studies have proposed that the diffusion of messenger molecules, such as monoamines, can mediate the plastic adaptation of synapses in supervised learning of neural networks. Based on these findings we developed a model for neural learning, where the signal for plastic adaptation is assumed …

#### Anthropic decision theory

This paper sets out to resolve how agents ought to act in the Sleeping Beauty problem and various related anthropic (self-locating belief) problems, not through the calculation of anthropic probabilities, but through finding the correct decision to make. It creates an anthropic decision theory (ADT…

#### Stock-out Prediction in Multi-echelon Networks

In multi-echelon inventory systems the performance of a given node is affected by events that occur at many other nodes and at many other time periods. For example, a supply disruption upstream will have an effect on downstream, customer-facing nodes several periods later as the disruption “c…

#### Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search

One of the most interesting features of Bayesian optimization for direct policy search is that it can leverage priors (e.g., from simulation or from previous tasks) to accelerate learning on a robot. In this paper, we are interested in situations for which several priors exist but we do not know in…

#### Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed a…

#### Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs

We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph. Namely, we use the support of its adjacency matrix to design learnable weight sharing filters able to exploit the underlying structure of signals in …

#### EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning

Objective: Electronic medical records (EMRs) contain an amount of medical knowledge which can be used for clinical decision support (CDS). Our objective is a general system that can extract and represent these knowledge contained in EMRs to support three CDS tasks: test recommendation, initial diag…

#### Doctoral Advisor or Medical Condition: Towards Entity-specific Rankings of Knowledge Base Properties [Extended Version]

In knowledge bases such as Wikidata, it is possible to assert a large set of properties for entities, ranging from generic ones such as name and place of birth to highly profession-specific or background-specific ones such as doctoral advisor or medical condition. Determining a preference or rankin…

#### A minimax and asymptotically optimal algorithm for stochastic bandits

We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions. We prove that it is simultaneously asymptotically optimal (in the sense of Lai and Robbins’ lower bound) and minimax optimal. This is the first algorithm proved t…

#### Open Source Dataset and Deep Learning Models for Online Digit Gesture Recognition on Touchscreens

This paper presents an evaluation of deep neural networks for recognition of digits entered by users on a smartphone touchscreen. A new large dataset of Arabic numerals was collected for training and evaluation of the network. The dataset consists of spatial and temporal touch data recorded for 80 …

#### Bandits with Delayed Anonymous Feedback

We study the bandits with delayed anonymous feedback problem, a variant of the stochastic $K$-armed bandit problem, in which the reward from each play of an arm is no longer obtained instantaneously but received after some stochastic delay. Furthermore, the learner is not told which arm an observat…

#### Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

To operate intelligently in domestic environments, robots require the ability to understand arbitrary spatial relations between objects and to generalize them to objects of varying sizes and shapes. In this work, we present a novel end-to-end approach to generalize spatial relations based on distan…

#### Temporal Pattern Mining from Evolving Networks

Recently, evolving networks are becoming a suitable form to model many real-world complex systems, due to their peculiarities to represent the systems and their constituting entities, the interactions between the entities and the time-variability of their structure and properties. Designing computa…

#### On the convergence of gradient-like flows with noisy gradient input

In view of solving convex optimization problems with noisy gradient input, we analyze the asymptotic behavior of gradient-like flows under stochastic disturbances. Specifically, we focus on the widely studied class of mirror descent schemes for convex programs with compact feasible regions, and we …

#### Label Distribution Learning Forests

Label distribution learning (LDL) is a general learning framework, which assigns to an instance a distribution over a set of labels rather than a single label or multiple labels. Current LDL methods have either restricted assumptions on the expression form of the label distribution or limitations i…

#### Contrastive Principal Component Analysis

We present a new technique called contrastive principal component analysis (cPCA) that is designed to discover low-dimensional structure that is unique to a dataset, or enriched in one dataset relative to other data. The technique is a generalization of standard PCA, for the setting where multiple …

#### Online Learning of a Memory for Learning Rates

The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online meta-learning algorithm that builds and optimizes a memory m…

You must be logged in to create new topics.