Pythonic AI
493 subscribers
317 photos
84 videos
67 files
538 links
منابع، دوره ها، همایشها ، مقالات و میم کامپیوتر
Download Telegram
End-to-end object detection with Transformers

#deeplearning #artificialintelligence

@pythonicAi
17 June
دوره تخصصی پردازش زبان طبیعی deeplearning.ai روی پلتفرم coursera منتشر میشه. به محض فراهم شدن شرایط این دوره ها در کانال قرار میگیره.

#deeplearning #artificialintelligence

@pythonicAi
This paper optimizes number of filter in each conv layer during training. It introduces a novel efficient oneshot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware.

https://openaccess.thecvf.com/content_CVPR_2020/papers/Berman_AOWS_Adaptive_and_Optimal_Network_Width_Search_With_Latency_Constraints_CVPR_2020_paper.pdf

#deeplearning #artificialintelligence

@pythonicAi
Forwarded from Pythonic AI (Soroush Hashemi far)
Deep Learning with Pytorch

Instructor: Alfredo Canziani

Link

#deeplearning #artificialintelligence #course

@pythonicAi
New banger from OpenAI – DALL·E (Dalí + WALL·E).

It generates images from text captions and it's amazing!

حالا میتونین مقالات علمی‌ای داشته باشین که متنش با مدل gpt-3 تولید شده و پلات‌هاش با dall-E رسم شده باشه :)

Link

#deeplearning #artificialintelligence #openai

@pythonicAi
​​MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs

Link

#deeplearning #artificialintelligence #gan

@pythonicAi
This media is not supported in your browser
VIEW IN TELEGRAM
Adversarial Latent Autoencoders (ALAE) not only generate 1024x1024 images with StyleGAN’s quality but also allow to manipulate real-world images in a feed-forward manner.

Paper

Code

#deeplearning #artificialintelligence #gan

@pythonicAi
MaskedFace-Net -- A Dataset of Correctly/Incorrectly Masked Face Images in the Context of COVID-19

By: Adnane Cabani, Karim Hammoudi, Halim Benhabiles, and Mahmoud Melkemi

Link

#dataset #machinelearning #deeplearning #artificialintelligence

@pythonicAi
Audio Deep Learning Made Simple: Automatic Speech Recognition (ASR), How it Works


Speech-to-Text algorithm and architecture, including Mel Spectrograms, MFCCs, CTC Loss and Decoder, in Plain English

Link

#machinelearning #deeplearning #speechrecognition #ctcloss

@pythonicAi
Online Berkeley Deep Learning Lectures 2021

University of Berkeley released its fresh course lectures online for everyone to watch. Welcome Berkeley CS182/282 Deep Learnings - 2021!

Link

#machinelearning #deeplearning #course #mooc #berkeley

@pythonicAi
The key idea behind the Convolutional Neural Nets:

The ability of learning networks can be greatly enhanced by providing constraints from the task domain.

Link

#deeplearning #convolution #neuralnetwork #machinelearning #article

@pythonicAi
Textless NLP: Generating expressive speech from raw audio

Generative Spoken Language Model (GSLM), the first high-performance NLP model that leverages recent breakthroughs in representation learning, allowing it to work directly from only raw audio signals, without any labels or text.

Link

#deeplearning #nlp #selfsupervised #facebook

@pythonicAi