MLconf NYC 2019
| title | author | length |
|---|---|---|
| Representations from natural language data: successes and challenges | Emily Pitler | 41m |
Overview of BERT as a bidirectional transformer pre-trained with masked tokens and a next-sentence objective, yielding state-of-the-art on SQuAD and many… | ||
| Machine Learning to Detect Illegal Online Sales of Prescription Opioids | Janani Kalyanam | 18m |
Pipeline ingests drug keyword streams via Twitter streaming API and collects ~1M tweets over months, applies a 2013 bi-term topic model to surface a… | ||
| Diagnostic Medical application of ML | Carrie Weinberg | 20m |
Amgen pilots machine vision with Zebra (FDA-cleared) to detect incidental vertebral compression fractures on CTs, finds labeling and workflow bottlenecks and… | ||
| Augmenting Mental Health Care in the Digital Age: Machine Learning as a Therapist Assistant | Niels Bantilian | 20m |
Describes a deployed crisis-risk alert built on anonymized Talkspace messages that flags potential self-harm and related crises and surfaces alerts routed to… | ||
| Using Network Analysis to Detect Kickback Schemes Among Medical Providers | Leanna Kent | 16m |
Builds a physician graph with edges weighted by the Jaccard index of shared patients, then runs a greedy egonet trimming algorithm that adds alters until… | ||
| Deep Learning Applications to Online Payment Fraud Detection | Nitin Sharma | 29m |
Speaker: Nitin Sharma
Slides: https://www.slideshare.net/SessionsEvents/nitin-sharma-deep-learning-applications-to-online-payment-fraud-detection
The talk… | ||
| Deep Reinforcement Learning based Insulin Controller for Effective Type-1 Diabetic Care | Liliana Cruz-Lopez | 19m |
Proposes a DDPG actor-critic insulin controller implemented in Python with SimGlucose + OpenAI Gym, trained and tested against a Padova-model baseline on 30… | ||
| A Bayesian Approach To Model Overlapping Objects Available As Distance Data | Sandhya Prabhakaran | 16m |
Introduces POCD, a Bayesian model that clusters objects directly from pairwise distance matrices allowing overlapping cluster membership via an IBP prior… | ||
| Hybrid ML Methods for the Interpretation and Integration of Heterogeneous Multimodal Data | Madalina Fiterau | 24m |
Hybrid pipelines produce concrete gains: a monitoring system that issues an alert every 90 seconds uses Viper partitions data into low‑dimensional views and… | ||
| Predicting Bond Prices: Regime Changes | Roy Lowrance | 21m |
Real-time engine BondDroid TM predicts bid and ask prices for thousands of corporate bonds using an ensemble of roughly 500 experts with varied look-back… | ||
| Reducing Operational Barriers to Model Training | Alexandra Johnson | 16m |
Hardware barriers fall but shipping experiments still stalls teams: initial workflow copies files via SCP and TMUX windows, then shifts to building a local… | ||
| Data-driven challenges in AI: scale, information selection, and safety | Anna Choromanska | 27m |
Proposes a new decision-tree objective that yields logarithmic prediction time and is optimized with SGD, demonstrating superior precision and prediction speed… | ||
| Personalizing Explainable Recommendations with Multi-objective Contextual Bandits | Rishabh Mehrotra | 22m |
Displays a contextual bandit deployed on Spotify’s homepage serving 100% traffic and trained as a multi-objective linear contextual bandit that optimizes a… | ||
| Building Machine Learning Models with Strict Privacy Boundaries | Renaud Bourassa | 14m |
Slack builds a single global search ranking model that preserves team boundaries by replacing high‑dimensional sensitive attributes with aggregated functions… | ||
| Developing large-scale machine learning algorithms on Amazon SageMaker | Amir Sadoughi | 19m |
Amazon SageMaker built-in algorithms are implemented as Docker containers using MXNet (and other frameworks like TensorFlow and PyTorch), support file mode vs… | ||
| Increasing the Impact of AI Through Better Software (Pytorch Updates) | Soumith Chintala | 19m |
A practical update on PyTorch: core pieces are an automatic-differentiation engine, a GPU-backed tensor library, optimizers and data loaders, and new tooling… | ||
| Using a Bayesian Neural Network in the Detection of Exoplanets | Esperanza López Aguilera | 23m |
NASA TESS simulated data covers 26 sectors with 27‑day watches at ~30‑minute cadence; processing yields 64,000 target stars and ~9,000 signals (~10,000 TCEs)… | ||
| Teaching a Machine to Code | Neel Sundaresan | 27m |
A production code-completion system is built from 700 cleaned C# repos (200k documents) using lightweight sequence/Markov models and a heavier AST-embedding… | ||
| nothing matches | ||