Главная
Study mode:
on
1
Intro
2
TRINITY FUELING ARTIFICIAL INTELLIGENCE
3
TASK: NAMED ENTITY RECOGNITION
4
RESULTS NER task on largest open benchmark (Onto-notes)
5
ACTIVE LEARNING WITH PARTIAL FEEDBACK
6
RESULTS ON TINY IMAGENET (100K SAMPLES) Accuracy vs. Mof Questions
7
TWO TAKE-AWAYS
8
CROWDSOURCING: AGGREGATION OF CROWD ANNOTATIONS
9
PROPOSED CROWDSOURCING ALGORITHM
10
LABELING ONCE IS OPTIMAL: BOTH IN THEORY AND PRACTICE
11
DATA AUGMENTATION 1: GENERATIVE MODELING
12
PREDICTIVE VS GENERATIVE MODELS
13
STATISTICAL GUARANTEES FOR THE NRM
14
NEURAL RENDERING MODEL (NRM)
15
NEURAL DEEP RENDERING MODEL (NRM)
16
DATA AUGMENTATION 2: SYMBOLIC EXPRESSIONS
17
ARCHITECTURE: TREE LSTM
18
SOME RESEARCH LEADERS AT NVIDIA
19
CONCLUSION Al needs integration of data, algorithms and infrastructure
Description:
Explore the fundamental components driving artificial intelligence in this 53-minute lecture from the Simons Institute Open Lecture Series. Delve into the AI Trinity of data, algorithms, and infrastructure as presented by Anima Anandkumar from the California Institute of Technology. Learn about named entity recognition, active learning with partial feedback, and crowdsourcing techniques for data annotation. Discover the power of data augmentation through generative modeling and symbolic expressions. Gain insights into neural rendering models and tree LSTM architectures. Understand the importance of integrating these three pillars for advancing AI technology, with examples from industry leaders at NVIDIA.

The AI Trinity - Data + Algorithms + Infrastructure

Simons Institute
Add to list