MLconf Atlanta 2017
2017-09-15
Atlanta, United States
who it's for
machine learning engineers, data scientists, applied research scientists, mlops engineers, nlp engineers, security engineers, computer vision engineers
topics
Bayesian hyperparameter optimization; mobile deep learning runtime; model quantization and sparsity; separable convolutions for edge; structure2vec graph embeddings; distributed convolutional networks in Spark; author node embeddings for NLP; Gaussian process soil moisture mapping; static VBA malware feature extraction; machine learning for attack classification; learning-to-rank for employer normalization; git-backed model and data versioning
| title | author | length |
|---|---|---|
| Best Practices for Hyperparameter Optimization | Alexandra Johnson | 18m |
A simple betting model beat the house using SigOpt after hyperparameter tuning, turning a losing approach into a money-making one and demonstrating real-world… | ||
| High Performance Deep Learning on Edge Devices With | Aran Khanna | 33m |
Apache MXNet ships a mobile runtime under 10 MB and shows a full vision network running near real time on a Raspberry Pi, using optimizations like separable… | ||
| Machine Learning Based Attack Vector Modeling for CyberSecurity | Ashrith Barthur | 22m |
Machine learning models classify DoS, recon, exploits and command‑and‑control by turning packet and aggregate logs into engineered variables like average TCP… | ||
| Productive Machine Learning and Deep Learning Projects | Greg Werner | 22m |
Platform design that decouples back end and front end and spawns language-specific containers (Python, R, Scala) with GPU access via an open wrapper for NVIDIA… | ||
| Graph Representation Learning with Deep Embedding Approach | Hanjun Dai | 21m |
Presents the structure2vec end-to-end graph embedding that maps node neighborhoods to vectors and is trained on supervised tasks; shows lower regression loss… | ||
| Making Natural Language Processing Robust to Sociolinguistic Variation | Jacob Eisenstien | 22m |
Shows that embedding author positions in social networks and adding two bilinear compatibility terms to a neural/structured model yields personalized… | ||
| Game of Drones | Jennifer Marsman | 28m |
FarmBeats pairs off‑the‑shelf drones, ground moisture probes (sensing at 4" and 12"), and aerial imagery to predict soil moisture across fields using Gaussian… | ||
| Convolutional Neural Networks at scale in | Jeremy Nixon | 21m |
Implemented convolutional neural nets inside Spark MLlib that run convolutions, max‑pooling and dense layers with a Keras-style Scala API, using distributed… | ||
| Support Vector Machine Modeling & Graph Theory Metrics for Disease Classification | Jessica Rudd | 15m |
Combines BRFSS survey data with a simulated small‑world social network (rewired lattice created in R) and runs SVMs in SAS alongside logistic regression; key… | ||
| Employer Name Normalization in the Online Recruitment Industry | Qiaoling Liu | 01h 33m |
CompanyDepot links employer strings from jobs and resumes to a CareerBuilder KB using Lucene indexing, query expansion from external mappings (Wikipedia… | ||
| Codifying Data Science Intuition | Ryan West | 17m |
Decision-theory minimax decision function selects the model that minimizes worst-case error across consecutive, temporally independent holdouts; implemented… | ||
| A Machine Learning approach for detecting a Malware | Talha Obaid | 27m |
Static static-analysis pipeline extracts VBA macro features (objects, goto counts, library calls, string ops, modules, forms), combines automated and… | ||
| Beyond a Bit Fit | Tim Chartier | 31m |
University program collects GPS, heart rate and impact streams from mouthpiece impact sensor, helmet sensors and a forthcoming headband with gyroscope, then… | ||
| Large Scale Graph Processing & Machine Learning Algorithms | Venkatesh Ramanathan | 26m |
PayPal converts HDFS logs into graphs with MapReduce (current pipeline takes ~two days) then experiments with a scale-up approach using 1.5 billion edges in… | ||
| Driving a Higher Level of Customer Support with Machine Learning | Yashar Mehdad | 30m |
Airbnb replaces brittle rules with an ML pipeline that classifies “trip vs non‑trip” tickets using escalations as gold labels, tackles 10:1 class imbalance… | ||
| nothing matches | ||