Anthill Inside 2017
| title | author | length |
|---|---|---|
| Synthetic Gradients – Decoupling Layers of a Neural Nets | Anuj Gupta | 41m |
Once in a while comes a (crazy!) idea that can change the very fundamentals of an area. In this talk, we will see one such idea that can change how neural… | ||
| AI: unleashing the next wave | Milind Hanchinmani | 30m |
Intel outlines concrete claims and tools: edge cameras and self-driving sensors produce 4000 GB per day and hospitals 3000 GB per week of data, requiring cloud… | ||
| Saving the Princess with Deep Learning | Navin Pai | 18m |
Deep Learning has provided an entirely new paradigm of solving problems which were otherwise deemed difficult to solve and is widely seen as a strong leap… | ||
| Hitchhiker’s Guide to Generative Adversarial Networks (GANs) | Ramanan Balakrishnan | 43m |
Generative Adversarial Networks claim to produce photorealistic samples using a generator and discriminator trained in a min/max game; convolutional… | ||
| Unsupervised and Semi-Supervised Deep Learning for Medical Imaging | Kiran Vaidhya | 33m |
Availability of labelled data for supervised learning is a major problem for narrow AI in current day industry. In imaging, the task of semantic segmentation… | ||
| Identifying Urban Makeshift Communities using satellite imagery and geo-coded data | Akarsh Zingade | 22m |
The aim of this talk is to provide a comprehensive description of the experimentation & explorations done by DataKind-Bangalore to identify non-permanent urban… | ||
| Adversarial attacks on deep learning models | Konda Reddy Mopuri | 44m |
Recent researh efforts show that deep learning models are vulnerable to small but structured perturbations. This quasi-imperceptible noise can fool the… | ||
| Keep Calm and Trust your Model - On Explainability of Machine Learning Models | Praveen Sridhar | 30m |
The accuracy of Machine Learning models is going up by the day with advances in Deep Learning. But this comes at a cost of explainability of these models… | ||
| How Deep is Deep Learning? | Amar Lalwani | 34m |
Undoubtedly Deep Learning is a recent significant step towards Artificial General Intelligence because of its sheer ability to learn most complex tasks. Deep… | ||
| PyTorch Demystified, Why Did I Switch | Sherin Thomas | 32m |
PyTorch claims practical wins from a Dynamic Computation Graph (autograd/Variable, .grad access, .cuda and NumPy bridges) and demonstrates them with an actual… | ||
| Apache MXNet, a highly memory efficient deep learning framework | Girish Patil | 20m |
GPU memory is the most expensive deep learning resource. MXNet was designed to allow complex deep learning with most minimal requirements on GPU memory. This… | ||
| nothing matches | ||