正在加载视频...
视频加载失败
.Jeff Dean 's full talk at NeurIPS 24 on Machine Learning for Systems and how Google thinks about these things
5 条评论
LLMSalaryman1 年前
@JeffDean Hats off to the researchers with the balls to name an unrelated lstm algo “llama” in 2024
dreaming android1 年前
@JeffDean Do you have youtube link?
FSDwhisper1 年前
@JeffDean Nice
Vibhu Pandey1 年前
@JeffDean @dwarkesh_sp
Rekha@031 年前
@JeffDean Great talk! What are the key takeaways?
相关视频
1:32
Sensitive content
We don’t talk enough about compatibility. Everyone obsesses over size, performance, and “how to last longer” but barely anyone talks about fit. Two bodies, two nervous systems, learning each other. Get the book now:
Caitlin V
71,403 次观看 • 2 个月前
![Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!](https://image.24vids.com/tw-2031397968511717584/amplify_video_thumb/2031397324404985860/img/FjgqUEEDb0gBsKbU.jpg)
