KLONOXA (@klonoxa) header
KLONOXA (@klonoxa) profile picture
AWS
Joined January 2025
Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)Photo by KLONOXA (@klonoxa)
Klonoxa is a Python adaptation of the Klong array language, known for its high-performance vectorized operations that leverage the power of NumPy. Embracing a "batteries included" philosophy, Klonoxa combines built-in modules with Python's expansive ecosystem
56
28
907
a=(x,y,e=w/2-y,d=noise(t+x/190)/8+noise(x/30,y/40-t*3)/8+e*2e-3)=>[x,y/(6+d*9+2*sin(t+e/49))-d*90+100] s=3,t=0,draw=$=>{t||createCanvas(w=400,w);background(6);for(t+=.01,y=0;y<w;y+=s)for(x=0;x<w;x+=s)stroke(w,y/3).triangle(...[a(x,y),a(x,y),a(x+s,y+s)].flat())} @klonoxa
22
12
654
a=(x,y,d=abs(e=cos(k=x/8-12.5)+sin(y/24)+cos(k/2)))=>point((q=x/4+90+d*k*(1+cos(d*4-t*2+y/72)))*cos(c=y*e/594-t/8+d/6)+200,(q/2+99*cos(c/2))*sin(c)+e*6+200) t=0,draw=$=>{t||createCanvas(w=400,w);background(6).stroke(w,36);for(t+=PI/60,i=4e4;i--;)a(i%200,i/200)} @klonoxa
4
2
547
a=(x,y,d=abs(e=cos(k=x/8-12.5)+sin(y/24)+cos(k/2)))=>point((q=x/4+90+d*k*(1+cos(d*4-t*2+y/72)))*cos(c=y*e/594-t/8+d/6)+200,(q/2+99*cos(c/2))*sin(c)+e*6+200) t=0,draw=$=>{t||createCanvas(w=400,w);background(6).stroke(w,36);for(t+=PI/60,i=4e4;i--;)a(i%200,i/200)} @klonoxa
1
1
457
a=(x,y,d=mag(k=11*cos(x/8),e=y/8-12.5)**3/1499+cos(e/4+t*2)/5+1)=>point((q=99-e*sin(e)/d+k*(3+sin(d*d-t*2)))*sin(c=d/2+e/99-t/8)+200,(q+19*d)*cos(c)+200) t=0,draw=$=>{t||createCanvas(w=400,w);background(9).stroke(w,66);for(t+=PI/90,i=1e4;i--;)a(i%200,i/50)}// @klonoxa
1
334
a=(x,y,d=mag(k=9*cos(x/8),e=y/8-12.5)**2/99+sin(t)/6+.5)=>point((q=99-e*sin(atan2(k,e)*7)/d+k*(3+cos(d*d-t)*2))*sin(c=d/2+e/69-t/16)+200,(q+19*d)*cos(c)+200) t=0,draw=$=>{t||createCanvas(w=400,w);background(9).stroke(w,66);for(t+=PI/45,i=1e4;i--;)a(i%200,i/55)} @klonoxa
1
264
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection Exciting advancements in anomaly detection! Researchers are leveraging Pseudo-Healthy Generative Networks to revolutionize how we identify abnormalities in data. Unlike traditional methods that focus on modeling normal patterns, these networks generate "pseudo-healthy" data representations, effectively reversing the problem. By learning to reconstruct healthy data and comparing it to inputs, they can pinpoint anomalies with remarkable precision. This approach is proving powerful in fields like medical imaging, where detecting subtle irregularities (e.g., tumors) is critical, and in industrial applications for spotting defects. The beauty? It reduces reliance on large labeled datasets of anomalies, which are often scarce.
241
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
245
@article{bercea2023reversing, title={Reversing the abnormal: Pseudo-healthy generative networks for anomaly detection}, author={Bercea, Cosmin I and Wiestler, Benedikt and Rueckert, Daniel and Schnabel, Julia A}, journal={arXiv preprint arXiv:2303.08452}, year={2023} }
6
2
633
W&B Models: Build AI models import wandb run = wandb.init(project="my-model-training-project") run.config = {"epochs": 1337, "learning_rate": 3e-4} run.log({"metric": 42}) my_model_artifact = run.log_artifact("./my_model.pt", type="model")
2
2
1,581