Depends on how experimental the idea is. Usually you want to start with something you know will work, and then try out one new idea at a time, each time persisting until you understand the results you're seeing fully.
INNOVATION
-
Dexterous Manipulation in Real Life Applications
By
–
dexterous manipulation in real life 👀 https://t.co/zOvBfvoeLi
— Yutaro Yamada (@_yutaroyamada) 8 janvier 2023dexterous manipulation in real life
-
AI Biology Applications: AlphaFold and Beyond Investment Focus
By
–
Biology is where we've seen some of the wildest and most important applications of AI to date. From AlphaFold to [redacted] to [redacted]… Psyched to keep investing in, and start writing about, this intersection with @ElliotHershberg in 2023.
-
Persistence: The Critical Virtue in Machine Learning Engineering
By
–
Perhaps the single most important virtue in ML engineering is persistence. The ML engineering process is one of repeatedly checking & understanding every detail of the system, until it finally goes through a phase transition from "not working at all" to "working shockingly well".
-
AI Breakthroughs 2022 Deep Learning Year in Review
By
–
¡1er VÍDEO DEL AÑO! 2022 : EL AÑO DE LA INTELIGENCIA ARTIFICIAL Pero… ¿Por qué? Hoy os traigo el resumen perfecto que recoge los avances más interesantes del mundo del Deep Learning del año pasado LINK: https://
youtu.be/rKJdwLkPPPM Bienvenidos a mi AI-REWIND 2022 -
Follow DAIR AI for Trending ML Papers Weekly
By
–
Follow us @dair_ai for upcoming trending ML papers of the week.
-
A Succinct Summary of Reinforcement Learning
By
–
A Succinct Summary of Reinforcement Learning. 11 of 11
-
Deep Learning Memorization: Understanding Overfitting Phenomena
By
–
This work aims to better understand how deep learning models overfit or memorize examples; interesting phenomena observed; important work toward a mechanistic theory of memorization. 8 of 11
-
StitchNet: Novel Neural Network Paradigm Through Pretrained Fragment Reuse
By
–
StitchNet is a novel paradigm to create new coherent neural networks by reusing pretrained fragments of existing NNs. 9 of 11
-
ConvNeXt V2: Performant CNN Model with Masked Autoencoder Framework
By
–
ConvNeXt V2 is a performant model based on a fully convolutional masked autoencoder framework and other architectural improvements. CNNs are sticking back! 6 of 11