Alex 徐瀚 retweeted
🚀 Exciting News! 🚀 Thrilled to announce that @NVIDIA has joined @sklearn_inria as a corporate sponsor! 🤝💡 Their commitment to advancing open-source software in #MachineLearning is stronger than ever. Together, let's push the boundaries of innovation! bit.ly/3SJAT6z
Alex 徐瀚 retweeted
I am grateful to have been a part of this work!
I really enjoyed using @DeepLabCut and B-SOiD @runninghsu to perform behavioural classification in ~185 hours of video.
This would not have been possible without these tools.
New work from the lab is out in @eLife! We used an experimenter-free touchscreen testing system from @phenosys to examine effects of activity-based anorexia on flexible learning & vice versa 🐁📲 @MonashBDI elifesciences.org/articles/8…
Alex 徐瀚 retweeted
If you want to remove unwanted objects or people from your pictures, use Lama Cleaner.
Lama Cleaner is a free and open-source tool powered by the SOTA AI model.
Link to Lama Cleaner: github.com/Sanster/lama-clea…
Alex 徐瀚 retweeted
PhD students, don't worry. Technologies, trends, and even whole fields come and go. A PhD makes you an expert in a field but, more importantly, teaches you how to become an expert. Once you know that you can learn anything, you can adapt to major disruptions in your field.
Alex 徐瀚 retweeted
Have you ever taken a while to come up with the visualizations for your data? With Lux, you can get some suggestions on what to visualize.
To use Lux, simply import it.
Link to Lux: buff.ly/3mO5r4g
#Python
Alex 徐瀚 retweeted
Now witness the power of this fully armed and operational battle (@DeepLabCut + B-SoiD) station
Alex 徐瀚 retweeted
A #Python function should only do one thing and have fewer than four arguments to make testing easier.
If a function only does one task but has more than three arguments, consider grouping the arguments using higher-level objects such as a dataclass.
Alex 徐瀚 retweeted
💥Preprint!💥 I am excited to show you our work “The therapeutic mechanism of deep-brain stimulation”! @_the_ing and I have worked on this for over 4 years. Big thanks to our co-authors @AlfredoElhz, @EnnyvBeest, @aishu1803, Peter, and Damiaan Denys (1/14) biorxiv.org/content/10.1101/…
Alex 徐瀚 retweeted
Graduate student @runninghsu, a member of the @YttriLab, analyzes complex neuroscience data with machine learning techniques.
cmu.edu/mcs/news-events/2022…
Alex 徐瀚 retweeted
Pls RT: @CmuScience is hosting meeting on the interface of ML with decision-making, behavioral detection, and imaging w/@gordonberman and @shreyaneuroctrl.
Great travel support and poster presentations available for trainees! Jan 12-13. hmu w/ any ???
cmu.edu/ai-physics-institute…
Alex 徐瀚 retweeted
Our new @biorxiv_neursci preprint by @EnrRodSeb & @Julio_EI is out! Ever wonder how to quantify representational structure over neural manifolds in high- and low-dim spaces? The structure index #SI is a graph-based metric applicable to any arbitrary space. biorxiv.org/content/10.1101/…
Alex 徐瀚 retweeted
It is common to use the if-else statements to execute multiple conditional statements.
In #Python 3.10 and above, you can use the switch statement to do the same thing.
Using the switch statement is cleaner than using multiple if-else statements.
Alex 徐瀚 retweeted
Super proud of @runninghsu giving a great talk yesterday (his first), and an awesome session of speakers on neural correlates of naturalistic behavior!!! #SfN22
I managed to sneak a picture of the crowd. Proud moment
Alex 徐瀚 retweeted
Replying to @YttriLab @kaymtye @eazim @CoryMillerMarmo @cris_niell @schneiderneuro @jesseGlab @SamWangPhD
Of course!! Already on my sched!
Here it is for other folks who might be interested:
103 - Network Dynamics During Naturalistic Behavior
Sun, Nov 13, 8am - 11:30am @ SDCC 23
abstractsonline.com/pp8/#!/1…
Alex 徐瀚 retweeted
Announcing Segmentation-Guided Contrastive Learning of Representations (SegCLR), a method that trains rich, generic representations of cellular morphology and ultrastructure without manual effort and can identify cell types from only small cell fragments→ goo.gle/3G2uIEh
Alex 徐瀚 retweeted
Super excited about this! Do your supervised behavioral classification better and with an order of magnitude less training data!
Thanks for great 3D monkey benchmark data from @MichaelLouisPl1 @DLBarack and the groundbreaking CalMS21 from @Antihebbiann @JenJSun
This Post is from an account that no longer exists. Learn more
Alex 徐瀚 retweeted
📣 Preprint alert 🚨
Excited to share “Facemap: a framework for modeling neural activity based on orofacial tracking”
#facemap biorxiv.org/cgi/content/shor…
See summary below🧵🧵🧵:


























![Markdown file with the following contents:
```mermaid
stateDiagram-v2
[*] --> Still
Still --> [*]
Still --> Moving
Moving --> Still
Moving --> Crash
Crash --> [*]
```](https://pbs.twimg.com/media/FhD3G6iXoAErMGo.png?name=small&format=webp)

