AI agents shouldn't be complex, heavy, or costly. baby-onit: one file, ~1,000 lines. Everything is traceable. Use @tavilyai and @OpenRouter or @vercel to start using agents without incurring initial costs. github.com/sibyl-oracles/babβ¦
2
130
Most ARM chips can't run decent AI models. Introducing EfficientSpeech, a 266k-param TTS model. Low cost ARM chips like in RPi4 can generate 104sec of speech mel spec in 1sec. Here's an AI-generated video w/ voice from EfficientSpeech. Info: github.com/roatienza/efficie⦠#ICASSP2023
We are lucky to have this paper accepted at ECCV 2022! More details later ... #ECCV2022
Scene Text Recognition with Permuted Autoregressive Sequence Models
deepai.org/publication/sceneβ¦
by Darwin Bautista and @jacobe
#Computation #Language
Rowel Atienza π΅π retweeted
Depth Pruning with Auxiliary Networks for TinyML
deepai.org/publication/depthβ¦
by Josen Daniel De Leon and @jacobe
#NeuralNetwork #ComputerScience
Rowel Atienza π΅π retweeted
.@Gradio & @huggingface for Rapid Deep Learning App Development by @jacobe
link: medium.com/@rowel/gradio-hugβ¦
Rowel Atienza π΅π retweeted
"The UP National Engineering Center Analytics and Data Science Certifications announced the development on Wednesday." gmanetwork.com/news/scitech/β¦ via @gmanews
Idea: If data augmentation improves model generalization, why not use it to generate 2 new inputs and force the representations to agree. Result: Additional model performance improvement. Comparison: Unlike Label Smoothing, the performance of our method, AgMax, is consistent.
Improving Model Generalization by Agreement of Learned Representations from Data Augmentation
deepai.org/publication/improβ¦
by @jacobe
#ComputerVision #ImageNet
Rowel Atienza π΅π retweeted
I am excited to share my latest work: 8-bit optimizers β a replacement for regular optimizers. Faster π, 75% less memory πͺΆ, same performanceπ, no hyperparam tuning needed π’. π§΅/n
Paper: arxiv.org/abs/2110.02861
Library: github.com/facebookresearch/β¦
Video: youtube.com/watch?v=IxrlHAJtβ¦
Rowel Atienza π΅π retweeted
Weβre introducing GSLM, the first language model that breaks free completely of the dependence on text for training. This βtextless NLPβ approach learns to generate expressive speech using only raw audio recordings as input. Learn more and get the code:
ai.facebook.com/blog/textlesβ¦
Rowel Atienza π΅π retweeted
Data Augmentation for Scene Text Recognition
deepai.org/publication/data-β¦
by @jacobe
#ComputerVision #ComputerVision
Rowel Atienza π΅π retweeted
ODSC APAC Virtual Conference Speaker: hubs.ly/H0V892b0 #ODSCAPAC #DataScience #DeepLearning @jacobe @upsystem
My 1st github project that reached the 1k milestone. @PacktPub github.com/roatienza
4
Rowel Atienza π΅π retweeted
GOO: A Dataset for Gaze Object Prediction in Retail Environments
deepai.org/publication/goo-aβ¦
by Henri Tomas et al. including @jacobe
#Estimator #Statistics
Rowel Atienza π΅π retweeted
Vision Transformer for Fast and Efficient Scene Text Recognition
deepai.org/publication/visioβ¦
by @jacobe
#ComputerVision #PatternRecognition
Yesterday, my former grad student Daryl gave a talk at Sony CSL Paris about his thesis on Next View Policy for 3D Reconstruction. Youtube: youtu.be/KdyDj3bjU0I
2
Rowel Atienza π΅π retweeted
After the Christmas break, we come back with our #enticelle seminar series! We welcome Daryl Peralta from @upsystem with his talk about βNext-Best View Policy for 3D Reconstructionβ. Register here to attend on Wednesday 13 at 11am (CET) csl.sony.fr/seminars/
Thanks @KirkDBorne !
Advanced #DeepLearning with #TensorFlow 2 and #KERAS: amzn.to/2B5svsg by @jacobe
βββββββ
#BigData #DataScience #AI #MachineLearning #DataScientists #ReinforcementLearning #NeuralNetworks #GANs #GenerativeAdversarialNetworks #ComputerVision #ObjectDetection
Rowel Atienza π΅π retweeted
Next-Best View Policy for 3D Reconstruction
pdf: arxiv.org/pdf/2008.12664.pdf
abs: arxiv.org/abs/2008.12664
Our paper Next-Best View Policy for 3D Reconstruction
was presented (oral) Aug 28 at ECCV 2020 Workshops. Key contribs: 1) 3K 3D House Models dataset 2)Learning algo to efficiently scan 3D houses. Paper: arxiv.org/abs/2008.12664 Youtube: youtu.be/OXynAHTDTTA
2
Rowel Atienza π΅π retweeted
Advanced Deep Learning with TensorFlow 2 and Keras 2nd Ed (@PacktPub) has been added to bookwatch. Author Rowel Atienza (@jacobe) introduces the practical side of deep learning i-programmer.info/book-watchβ¦


















