Google & UCLA Formulate Algorithm Discovery as Program Search, Yielding ‘Lion’ for SOTA DNN Optimization https://
syncedreview.com/2023/02/21/goo
gle-ucla-formulate-algorithm-discovery-as-program-search-yielding-lion-for-sota-dnn-optimization/
…
MACHINE LEARNING
-
Google UCLA Discover Lion Algorithm for DNN Optimization
By
–
-
ControlNet Paper: A Deep Learning Enthusiast’s Dream Abstract
By
–
El abstract del paper de ControlNet parece una carta a los reyes magos de cualquier fan del Deep Learning
-
Robots Learn Natural Language Communication and Real-World Skills
By
–
Part 6 in the series is out, discussing our work in robotics, especially allowing robots & humans to communicate naturally via language, apply common sense knowledge in real-world situations & increasing the number of low-level skills robots can perform.
-
Part 5: Scalable Algorithms, Privacy, and Causal Inference
By
–
Part 5 in the series is out, posted by @Mirrokhni on behalf of many, covering advances in:
· Scalable algorithms (esp. for graphs and clustering)
· Privacy and federated learning
· Market algorithms & causal inference
· Algorithmic foundations and theory -
AI and Big Data Analytics as Future Competitive Advantages
By
–
AI and Big data Analytics are the future competitive advantages #AI #bigdata
-
Survey on Efficient Training Methods for Transformer Architectures
By
–
A Survey on Efficient Training of Transformers Transformers are the one architecture driving AI research in most modalities. They require large compute resources, but more and more efficient training approaches are being proposed. A survey on the topic: https://
arxiv.org/abs/2302.01107 -
Unimodal Text Models Unfairly Compared in Visual QA Tasks
By
–
Lo vi y lo estuve estudiando meter en el vídeo PEEEEEERO tiene un poco de trampa. Comparar modelos unimodales de texto (ciegos como GPT 3.5) en tareas de QyA visuales es un poco raro. Y más teniendo la opción de validarlo contra BLIP.
-
DataRobot Model Selection Using Evaluation Metrics
By
–
We recently went live on LinkedIn with DataRobot Senior Data Scientist, Taylor Larkin, who led a discussion on selecting DataRobot models based on user-specified evaluation metrics. Check it out if you missed it! #aiaccelerators https://
linkedin.com/feed/update/ur
n:li:activity:7029491637332381697
… -
Combinatorial Optimization and RL Shape Future Game Design
By
–
Overall, cool paper about a funny application of combinatorial optimization. Jokes aside, RL and optimization are probably the future of game design. At least for puzzle games. 🙂
-
Genetic Algorithm for Puzzle Solving with Diversity Selection
By
–
Next, solving puzzles. The authors used a custom GA: 1/ Initialization using the previous algorithm 2/ Crossover/Mutation with a uniform crossover operation 3/ Find feasible solutions and "heal" broken ones 4/ Selection with a diversity criterion