Anthill Inside 2018
| title | author | length |
|---|---|---|
| The art and science of making computers understand sentiment and emotion | Pushpak Bhattacharyya | 39m |
Claims concrete outcomes: a working emoji-suggestion pipeline trained on ~900,000 tweets (140,000 with emoji), 137 frequent emojis, train 82k/val 2k/test 2k… | ||
| Uncertainty in deep learning | Madhu Gopinathan | 35m |
Builds a Bayesian NN with weight distributions using variational inference (Gaussian mean and sigma, reparameterization trick) so predictions come from many… | ||
| Building Knowledgeable Machines | Partha Talukdar | 44m |
Argues that large knowledge graphs materially improve AI decision making and shows concrete methods and results: a continuous reader NELL (running since 2010)… | ||
| Learning Real-time Object Detection In The Absence of Large-scale Datasets | Vijay Gabale | 39m |
This talk will focus an area of computer vision, object detection, that involves automatically localising and classifying different objects from photos and… | ||
| Sarcasm Detection: Achilles Heel of sentiment analysis | Anuj Gupta | 37m |
Sentiment analysis has been for long poster boy problem of NLP and has attracted a lot of research. However, despite so much work in this sub area, most… | ||
| The evolution in AI thinking and products of the next decade | Shailesh Kumar | 59m |
Argues that AI moves from infrastructure → automation → data → AI to a new layer of multiagent, connected products and gives concrete targets: product 3.0… | ||
| Product Size Recommendation for Fashion E-commerce | lavanya TS | 22m |
Paper claims a probabilistic size-recommendation system that reduces size-related returns by inferring a latent customer true size and product true size and… | ||
| Looking beyond LSTMs: Alternatives to Time Series Modelling using Neural Nets | Aditya Patel | 25m |
Claims that convolutional architectures beat LSTMs on noisy physiological vitals: experiments on the MIMIC dataset use two hours of inputs (150 samples) to… | ||
| nothing matches | ||