🎓 PhD candidate in Deep Learning for Remote Sensing data at UGR 🛰️
Granada, Spain
Joined October 2021
- Tweets889
- Following329
- Followers681
- Likes759
Jose Rodríguez retweeted
i understand you guys like lists
LeNet (1989)
LSTM (1997)
Deep Belief Networks (2006)
AlexNet (2012)
Word2Vec (2013)
GAN (2014)
VGG16/19 (2014)
InceptionNet (2014)
VAE (2014)
ResNet (2015)
U-Net (2015)
YOLO v1 (2015)
FastRCNN (2015)
FasterRCNN (2015)
Neural Style Transfer (2015)
Original Diffusion Models (2015)
SSD (2016)
DCGAN (2016)
AlphaGo(2016)
SqueezeNet (2016)
Transformer (2017)
CycleGAN (2017)
MobileNet (2017)
DenseNet (2017)
Mask R-CNN (2017)
BERT (2018)
YOLOv3 (2018)
BigGAN (2018)
StyleGAN (2018)
GPT-2 (2019)
DistilBERT (2019)
RoBERTa (2019)
XLNet (2019)
StyleGAN2 (2019)
DDPM (2020)
GPT-3 (2020)
DETR (2020)
DeiT (2020)
DALL-E (2020)
Alphafold 2
T5 (2020)
AlphaFold(2020)
GLIDE (2021)
CLIP (2021)
ViT (2021)
Swin Transformer (2021)
StyleGAN3 (2021)
Imagen (2022)
Flow Matching (2022)
Stable Diffusion (2022)
YOLOv7 (2022)
PaLM (2022)
GPT-4 (2023)
DINO v2 (2023)
SDXL (2023)
SAM (2023)
Alphafold 3 (2024)
🤯 Recently getting into LLM Agents 🤯
Amazed by the improvement they suppose over using a "plain" LLM
Four AI Agent Strategies That Improve GPT-4 and GPT-3.5 Performance buff.ly/3ydMdAc
Jose Rodríguez retweeted
I have been training Deep Learning models for 4 years now.
⚡ I can say that @LightningAI has been the most transformative library to improve my Deep Learning workflow. ⚡
Here are 5 benefits of using it:
The AI revolution is reshaping industries, but will it fully replace personal trainers, coaches, physicians, and therapists? I think not. Here's why:
Human connection is irreplaceable in these fields. The empathy, trust, and emotional support provided by professionals can't be authentically replicated by AI. Consider a therapist reading subtle body language or a coach motivating an athlete - these require intuition and emotional intelligence that AI lacks.
Humans excel at contextual understanding, reading between the lines, and adapting on the fly. We make complex ethical decisions using wisdom and experience, crucial in fields like medicine. Our creativity allows us to craft unique solutions drawing from diverse experiences.
AI will definitely transform these professions, but in the form of augmentation, not replacement. AI could handle data analysis, assist diagnoses, or generate plans, freeing professionals to focus on human interaction. Imagine doctors using AI to analyze complex data, allowing more time for patient care.
Regulatory and trust factors also play a role. Many are uncomfortable with AI fully managing their health without human oversight.
The future likely holds a synergy between humans and AI, potentially leading to enhanced services and better outcomes. It's not human vs. AI, but human + AI.
As my Machine Learning / Deep Learning projects grew, managing configs became a nightmare.
Messy code, lost experiments – sound familiar? 😓 I've been exploring Hydra, a Python library for efficient configuration management. It's helping me create dynamic, hierarchical configs easily. Still learning, but already seeing cleaner code and better experiment tracking. No more manual dict setups! 🎉
How do you handle config chaos in your ML projects? Any favorite tools? 🤔
Hydra webpage link: hydra.cc/
Jose Rodríguez retweeted
Understanding Deep Learning
Impressive new book on understanding deep learning concepts.
Topics include fundamental building blocks, Transformers, GNNs, RL, diffusion models, and more.
Probably one of the most comprehensive and up-to-date overviews of deep learning that exist today.
I have been training Deep Learning models for 4 years now.
⚡ I can say that @LightningAI has been the most transformative library to improve my Deep Learning workflow. ⚡
Here are 5 benefits of using it:
That's the end of the thread 🧵
For more helpful content on AI 🤖 follow me here @RodOrtJose ✅
I'm sharing my learning experience over here
⚡️ Discovering @LightningAI has been one the main improvements in my neural networks experimentation workflow ⚡️
In the upcoming days I will post a thread explaining how it's making the difference for me!!
Jose Rodríguez retweeted
The Transformer is a magnificient neural network architecture because it is a general-purpose differentiable computer. It is simultaneously:
1) expressive (in the forward pass)
2) optimizable (via backpropagation+gradient descent)
3) efficient (high parallelism compute graph)
Jose Rodríguez retweeted
Every year I teach CS theory, I find that I need to apologize less and less about having so much math content. CS practice is getting more & more mathy.
Now I just ask students if they want to their future job to be one where they read texts of first type, or the second type:
Jose Rodríguez retweeted
First Principles of Computer Vision, Columbia University
Really nice lectures on the physical and mathematical foundations of computer vision.
140 videos that you can watch at your pace. Slides are also provided to follow along.
Jose Rodríguez retweeted
most common neural net mistakes: 1) you didn't try to overfit a single batch first. 2) you forgot to toggle train/eval mode for the net. 3) you forgot to .zero_grad() (in pytorch) before .backward(). 4) you passed softmaxed outputs to a loss that expects raw logits. ; others? :)
