Es decir, la red que nos ha creado, como sólo tiene una capa, se ajusta pobremente a los datos y quizás no se vé tan espectacular. Pero la tarea que le hemos pedido está perfectamente hecha. Datos en espiral. Una red neuronal. Visualización. MP4 animado del training.
RESEARCH
-
AI Neural Network Classifies Spiral Dataset with Decision Boundaries
By
–
Y aquí lo tenéis! El resultado del código creado en el directo, donde le hemos pedido a la IA que programe una red neuronal que clasifique un dataset de datos en forma de espiral, mostrando las fronteras de decisión en azul y rojo.
— Carlos Santana (@DotCSV) 12 février 2023
La red y la clasificación es simple, pero wow!! pic.twitter.com/36GxgxbN7CY aquí lo tenéis! El resultado del código creado en el directo, donde le hemos pedido a la IA que programe una red neuronal que clasifique un dataset de datos en forma de espiral, mostrando las fronteras de decisión en azul y rojo. La red y la clasificación es simple, pero wow!!
-
The One Secret to Know About AI
By
–
The one secret to know about AI https://
thetechnologyletter.com/the-posts/the-
one-secret-to-know-about-ai
… // $MSFT $GOOGL $AMZN // @OpenAI #deeplearning #AI #artificialintelligence #engineering #manufacturing #MachineLearning -
Survey on Transformers Applications in Reinforcement Learning
By
–
A Survey on Transformers in Reinforcement Learning Transformers have been the prime mover of almost all modalities, from vision, speech, text and are showing potential applications in RL. This survey paper provides a nice taxonomy of Transformers in RL. https://
arxiv.org/abs/2301.03044 -
LLM Criticism and Mathematical Understanding Behind Models
By
–
I find the criticism of his piece absurd, but it was hardly meant for people who “understand the matrix math” behind a LLM.
-
Explaining GPT limitations rationally against hype
By
–
That just says it is wrong but doesn’t offer a rationale. I think it is quite a useful way to explain what gtp does and why it is limited. And that is really needed when there is so much hyperbole and over-extrapolation.
-
Ted Chiang analyzes ChatGPT’s underlying mechanisms and implications
By
–
Ted Chiang, a brilliant scifi writer, wrote a brilliant piece on ChatGPT. Well worth reading if you want to understand what’s really going on behind the prompt. https://
newyorker.com/tech/annals-of
-technology/chatgpt-is-a-blurry-jpeg-of-the-web/amp
… -
Step-by-Step Thinking Needs Correct Answers in GPT Models
By
–
One of my favorite results in 2022 was that it's not enough to just think step by step. You must also make sure to get the right answer 😀 https://
sites.google.com/view/automatic
-prompt-engineer
…
(actually a nice insight into a psychology of a GPT; it pays to condition on a high reward) -
ML Professional Launches GNN Book, Joins JPMorgan UK Team
By
–
Back on Twitter after a few chaotic months! A few updates: – I moved to the UK and joined an excellent machine learning team @jpmorgan – I'm publishing a book about Graph Neural Networks for practitioners Stay tuned for more 🙂
-
Backpropagation: Essential for Training Deep Neural Networks
By
–
This is very important in Deep Learning: it allows calculating derivatives of highly complex neural networks, composed of stacked layers of simple functions. Gradient descent is used to update the neural net weights, allowing it to learn from data and perform complex tasks.