Jose Rodríguez

🎓 PhD candidate in Deep Learning for Remote Sensing data at UGR 🛰️

[Jose Rodríguez @RodOrtJose]

This is true even right now. With the week to week advancing pace we are seeing nowadays it’s not worth an AI degree focused on the latest tools/methods, since they will be outdated soon.

If you study a fundamental degree like the ones you listed, put some computer science basics, and study a resource examining the foundations of AI/DL on it, you are ready to go. In fact, the fundamentals of modern AI are very simple maths.

PD: I am going through the new DL book from C. Bishop and I think could be a fantastic resource to learn these foundations.

https://t.co/Op9iEBe2Gg

[Jose Rodríguez @RodOrtJose]

@karpathy @ai_bites What a helpful app. Are you considering to release the app/code?

If not, please consider it 🙏🏼

It would be great to ask the LLM to break down complex concepts, ask follow up questions…

I think it’s an invaluable learning tool

[Jose Rodríguez @RodOrtJose]

@fran_cotan Alguien se podría preguntar que por qué DeepSeek/China querrían perder dinero. La respuesta podría ser que quieran conseguir datos de los usuarios para mejorar sus sistemas. Actualmente todas las grandes compañías de IA son americanas y se llevan todo el tráfico de datos.

[Jose Rodríguez @RodOrtJose]

@fran_cotan (1) de verdad la mejora en eficiencia es tan grande que permite reducir tanto el precio, (2) que no haya tanta diferencia y la reducción de precio sea a costa perder muuucho dinero o (3) una combinación de las dos anteriores.

[sankalp @dejavucoder]

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)

[Jose Rodríguez @RodOrtJose]

Yes, the self-motivated ones will learn on his own but definetely we can have more motivated students if AI is correctly taught at an early course.

At the end of the day you only need Calculus, Linear Algebra, Statistics and basic programming, which is usually taught in the first course.

IMHO few students are really capable to learn on his own at that early stages, the others also deserves the opportunity to get early in the field.

[Jose Rodríguez @RodOrtJose]

🤯 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 https://t.co/8CE0viETB8

[Jose Rodríguez @RodOrtJose]

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:

[Jose Rodríguez @RodOrtJose]

@_neilbhatt @LightningAI Thanks to you and all the people developing the product

It’s really helpful

[Jose Rodríguez @RodOrtJose]

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:

[Jose Rodríguez @RodOrtJose]

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.

[Jose Rodríguez @RodOrtJose]

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: https://t.co/25jFyRRGq8

[Jose Rodríguez @RodOrtJose]

@_neilbhatt @LightningAI Already posted it! You can find it in my profile 😁

[Jose Rodríguez @RodOrtJose]

⚡️ 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!!

[elvis @omarsar0]

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.

[Jose Rodríguez @RodOrtJose]

@LightningAI 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

[Jose Rodríguez @RodOrtJose]

@LightningAI If you want to give it a try see: https://t.co/mtHOCUYmL2