این قسمت جدید پادکست مهندسی اسپاتیفای دیروز اومده و راجع به یه پروژه خیلی خفن جدیدشونه:
What if you could create a guitar solo just by humming it? That’s Basic Pitch, a new open source project from Spotify’s Audio Intelligence Lab. Basic Pitch is a neural network that can analyze the recording of almost any instrument (including your voice) and then transcribe the notes that it detects into MIDI, the standard file format used for musical notation. It’s like speech-to-text, except it’s turning musical performances — whatever you hum, strum, pluck, peck, or tinkle — into a digital score you can edit on your computer.
Hear host Dave Zolotusky talk with Spotify researcher Rachel Bittner about what makes detecting musical notes an interesting machine learning problem. You’ll learn about how musicians use audio-to-MIDI converters to make music, the subtleties of pitch tracking, and why you want your model to capture the main pitch events in the audio as well as all the “wiggly stuff”. Plus, a live demo of the model in action and all the “Hot Cross Buns” you can handle.
https://open.spotify.com/episode/4wDDgWn037xjuq4Hr0u6a3?si=6eGcFmocRImv_frDLUBovw&utm_source=copy-link
What if you could create a guitar solo just by humming it? That’s Basic Pitch, a new open source project from Spotify’s Audio Intelligence Lab. Basic Pitch is a neural network that can analyze the recording of almost any instrument (including your voice) and then transcribe the notes that it detects into MIDI, the standard file format used for musical notation. It’s like speech-to-text, except it’s turning musical performances — whatever you hum, strum, pluck, peck, or tinkle — into a digital score you can edit on your computer.
Hear host Dave Zolotusky talk with Spotify researcher Rachel Bittner about what makes detecting musical notes an interesting machine learning problem. You’ll learn about how musicians use audio-to-MIDI converters to make music, the subtleties of pitch tracking, and why you want your model to capture the main pitch events in the audio as well as all the “wiggly stuff”. Plus, a live demo of the model in action and all the “Hot Cross Buns” you can handle.
https://open.spotify.com/episode/4wDDgWn037xjuq4Hr0u6a3?si=6eGcFmocRImv_frDLUBovw&utm_source=copy-link
برای اینکه بعدا بتونم به خودم یادآوری کنم:
این پیامها و «هنوز»مطالعهکردنها در حالیه که نزدیک سه چهار ساعته که به شدت گریه کردم و باز بغض دارم. So keep going
این پیامها و «هنوز»مطالعهکردنها در حالیه که نزدیک سه چهار ساعته که به شدت گریه کردم و باز بغض دارم. So keep going
👏2
Awesome Diffusion Models
A fantastic and well-organized collection of learning resources on diffusion models such as introductory papers, survey papers, intro videos, long lectures, and blog posts. Papers in vision, natural language, tabular, graph, etc.
https://twitter.com/Jeande_d/status/1578482659105218560?t=SHrOg23xJxvraHToF2zxQw&s=19
A fantastic and well-organized collection of learning resources on diffusion models such as introductory papers, survey papers, intro videos, long lectures, and blog posts. Papers in vision, natural language, tabular, graph, etc.
https://twitter.com/Jeande_d/status/1578482659105218560?t=SHrOg23xJxvraHToF2zxQw&s=19
SUT Twitter
چقدر خوب خونده رعنا منصور آهنگ شروین رو: #مهسا_امینی #MahsaAmini #Woman_Life_Freedom ◍Ped◍ @sut_tw
Audio
خیلی حال کردم باهاش
Baraye
Rana Mansour
Baraye
Rana Mansour
My Iran (Feat. Erfan, Gdaal, Rana Mansour, Hamed Nikpay)
King Raam
├🎤 By: King Raam
├🎵 Song: My Iran (Feat. Erfan, Gdaal, Rana Mansour, Hamed Nikpay)
├🎺 Genre: Rock
Nice job 👍
├🎵 Song: My Iran (Feat. Erfan, Gdaal, Rana Mansour, Hamed Nikpay)
├🎺 Genre: Rock
Nice job 👍
AtHomeWithAI - Curated Resource List, DeepMind
A list of educational resources curated by people at DeepMind for anyone interested in learning AI, machine learning, and other related topics.
https://twitter.com/Jeande_d/status/1580641346452262913?t=yT6XOCyqOcoS4RHIO3Q4YA&s=19
A list of educational resources curated by people at DeepMind for anyone interested in learning AI, machine learning, and other related topics.
https://twitter.com/Jeande_d/status/1580641346452262913?t=yT6XOCyqOcoS4RHIO3Q4YA&s=19
این مقاله که سه چهار روز پیش منتشر شده، اثبات و بازنماییای از شبکههای عصبی داره و ادعا کرده که اونها رو از یک مدل black box خارج میکنه و تغییرپذیر (interpretable) میشن!
چیز جالبی به نظر میرسه
In this manunoscript, we show that any neural network having piece-wise linear activation functions can be represented as a decision tree. The representation is equivalence and not an approximation, thus keeping the accuracy of the neural network exactly as is. This equivalence shows that neural networks are indeed interpretable by design and makes the \textit{black-box} understanding obsolete. We share equivalent trees of some neural networks and show that besides providing interpretability, tree representation can also achieve some computational advantages. The analysis holds both for fully connected and convolutional networks, which may or may not also include skip connections and/or normalizations.
https://arxiv.org/abs/2210.05189
چیز جالبی به نظر میرسه
In this manunoscript, we show that any neural network having piece-wise linear activation functions can be represented as a decision tree. The representation is equivalence and not an approximation, thus keeping the accuracy of the neural network exactly as is. This equivalence shows that neural networks are indeed interpretable by design and makes the \textit{black-box} understanding obsolete. We share equivalent trees of some neural networks and show that besides providing interpretability, tree representation can also achieve some computational advantages. The analysis holds both for fully connected and convolutional networks, which may or may not also include skip connections and/or normalizations.
https://arxiv.org/abs/2210.05189
📣Big news!!!
Pandas DataFrame output is now available for all sklearn transformers (in dev)! This will make running pipelines on dataframes soo much easier, and provides better ways to track feature names!
🔥This is one of the biggest improvements in scikit-learn in a long time and we'd love your feedback! Please try out the nightly built and give it a go!
https://scikit-learn.org/dev/auto_examples/miscellaneous/plot_set_output.html#sphx-glr-auto-examples-miscellaneous-plot-set-output-py
Pandas DataFrame output is now available for all sklearn transformers (in dev)! This will make running pipelines on dataframes soo much easier, and provides better ways to track feature names!
🔥This is one of the biggest improvements in scikit-learn in a long time and we'd love your feedback! Please try out the nightly built and give it a go!
https://scikit-learn.org/dev/auto_examples/miscellaneous/plot_set_output.html#sphx-glr-auto-examples-miscellaneous-plot-set-output-py
❤1