Uploaded September 2025 | Updated November 2026, 3 hours ago
In this video, we take a look 1x1 convolutions (point wise convolutions) and demonstrate what they are, why they are useful, architecture diagrams and PyTorch code!
ABOUT ME
⭕ Subscribe: youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: medium.com/@dataemporium
💻 Github: github.com/ajhalthor
👔 LinkedIn: linkedin.com/in/ajay-halthor-477974bb
RESOURCES
[1 📚] Slides used in the video: link.excalidraw.com/p/readonly/7aEsWmuZNQK4SE2IHzWn
[2 📚] Main paper of the video that introduces 1x1 convolutions: arxiv.org/pdf/1312.4400
[3 📚] Code + Diagrams used in the video: github.com/ajhalthor/computer-vision-101/tree/main/pointwise_convolution
[4 📚] Paper that visualizes what each layer of the convolution networks learn: arxiv.org/pdf/1311.2901
[5 📚] Main paper that introduced AlexNet: proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: youtube.com/playlist?list=PLTl9hO2Oobd9kS--NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
⭕ ChatGPT Playlist: youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V
⭕ Coding Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: imp.i384100.net/MathML
📕 Calculus: imp.i384100.net/Calculus
📕 Statistics for Data Science: imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: imp.i384100.net/BayesianStatistics
📕 Linear Algebra: imp.i384100.net/LinearAlgebra
📕 Probability: imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: imp.i384100.net/Deep-Learning
📕 Python for Everybody: imp.i384100.net/python
📕 MLOps Course: imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): imp.i384100.net/NLP
📕 Machine Learning in Production: imp.i384100.net/MLProduction
📕 Data Science Specialization: imp.i384100.net/DataScience
📕 Tensorflow: imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is 1x1 convolution?
01:00 Walking through an AlexNet architecture diagram
03:10 Some problems with the architecture
07:08 Rewrite architecture using 1x1 convolutions
16:20 Coding 1x1 convolutions and comparing performance with/without it.
19:17 Quiz Time
20:11 Summary
In this video, we take a look 1x1 convolutions (point wise convolutions) and demonstrate what they are, why they are useful, architecture diagrams and PyTorch code!
ABOUT ME
⭕ Subscribe: youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: medium.com/@dataemporium
💻 Github: github.com/ajhalthor
👔 LinkedIn: linkedin.com/in/ajay-halthor-477974bb
RESOURCES
[1 📚] Slides used in the video: link.excalidraw.com/p/readonly/7aEsWmuZNQK4SE2IHzWn
[2 📚] Main paper of the video that introduces 1x1 convolutions: arxiv.org/pdf/1312.4400
[3 📚] Code + Diagrams used in the video: github.com/ajhalthor/computer-vision-101/tree/main/pointwise_convolution
[4 📚] Paper that visualizes what each layer of the convolution networks learn: arxiv.org/pdf/1311.2901
[5 📚] Main paper that introduced AlexNet: proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: youtube.com/playlist?list=PLTl9hO2Oobd9kS--NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
⭕ ChatGPT Playlist: youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V
⭕ Coding Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: imp.i384100.net/MathML
📕 Calculus: imp.i384100.net/Calculus
📕 Statistics for Data Science: imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: imp.i384100.net/BayesianStatistics
📕 Linear Algebra: imp.i384100.net/LinearAlgebra
📕 Probability: imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: imp.i384100.net/Deep-Learning
📕 Python for Everybody: imp.i384100.net/python
📕 MLOps Course: imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): imp.i384100.net/NLP
📕 Machine Learning in Production: imp.i384100.net/MLProduction
📕 Data Science Specialization: imp.i384100.net/DataScience
📕 Tensorflow: imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is 1x1 convolution?
01:00 Walking through an AlexNet architecture diagram
03:10 Some problems with the architecture
07:08 Rewrite architecture using 1x1 convolutions
16:20 Coding 1x1 convolutions and comparing performance with/without it.
19:17 Quiz Time
20:11 Summary


![The AI that DOMINATED segmentation ...
How did Transformers dominate Image Segmentation? Lets talk about this to paint this fascinating story.
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: https://medium.com/@dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 📚] Fully Connected Networks paper: https://arxiv.org/pdf/1411.4038
[2 📚] MaskRCNN paper: https://arxiv.org/pdf/1703.06870
[3 📚] MaskRCNN video on my channel: https://youtu.be/oxTpAhTVSBU?si=ZT0Rak7t0Z5ERzN5
[4 📚] MaskFormer paper: https://arxiv.org/pdf/2107.06278
[5 📚] Mask2Former paper: https://arxiv.org/pdf/2112.01527
[6 📚] SAM 1 paper: https://arxiv.org/pdf/2304.02643
[7 📚] SAM 2 paper: https://arxiv.org/pdf/2408.00714
[8 📚] SAM 3 paper: https://arxiv.org/pdf/2511.16719
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: https://www.youtube.com/playlist?list=PLTl9hO2Oobd97qfWC40gOSU8C0iu0m2l4
⭕ ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
⭕ Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: https://imp.i384100.net/MathML
📕 Calculus: https://imp.i384100.net/Calculus
📕 Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
📕 Linear Algebra: https://imp.i384100.net/LinearAlgebra
📕 Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
📕 Python for Everybody: https://imp.i384100.net/python
📕 MLOps Course: https://imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): https://imp.i384100.net/NLP
📕 Machine Learning in Production: https://imp.i384100.net/MLProduction
📕 Data Science Specialization: https://imp.i384100.net/DataScience
📕 Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 Introduction
00:50 Pixel Classification with Convolutional Networks
01:42 Mask classification with MaskFormer
02:58 Issue with Transformers
03:16 Efficient Mask2Former
04:30 Moving beyond predetermined classes with SAM
05:45 Extending segmentation to video with SAM 2
06:32 Extending segmentation to multiple objects with SAM 3
08:58 Putting it all together The AI that DOMINATED segmentation ...](https://i.ytimg.com/vi/c06sW_lyX10/mqdefault.jpg)
![Depthwise Separable Convolutions - Explained!
In this video, we take a look at depthwise separable convolutions. What is it? How does it work? Why do it? Code included!
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: https://medium.com/@dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 📚] Slides: https://link.excalidraw.com/p/readonly/nTbHqs6Z6NhUWvvaQ1Zq
[2 📚] Code: https://github.com/ajhalthor/computer-vision-101/blob/main/depthwise_separable_convolution/depthwise_separable_convolutions.ipynb
[3 📚] Xception (paper that uses DSC): https://arxiv.org/pdf/1610.02357
[4 📚] Mobile Nets (paper that uses DSC): https://arxiv.org/pdf/1704.04861.pdf
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
⭕ ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
⭕ Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: https://imp.i384100.net/MathML
📕 Calculus: https://imp.i384100.net/Calculus
📕 Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
📕 Linear Algebra: https://imp.i384100.net/LinearAlgebra
📕 Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
📕 Python for Everybody: https://imp.i384100.net/python
📕 MLOps Course: https://imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): https://imp.i384100.net/NLP
📕 Machine Learning in Production: https://imp.i384100.net/MLProduction
📕 Data Science Specialization: https://imp.i384100.net/DataScience
📕 Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is Depthwise Separable Convolution?
00:55 How standard convolution works
03:17 How depthwise separable convolution works
07:06 Key insight comparing the 2
08:39 Code
12:39 Quiz Time
13:35 Summary Depthwise Separable Convolutions - Explained!](https://i.ytimg.com/vi/c8LlZuXOCxg/mqdefault.jpg)

![The Origin of Language Models (like ChatGPT)
SPONSOR
Get 20% off and be apart of a Premium Software Engineering Community for career advice and guidance: jointaro.com/r/ajayh486
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: https://medium.com/@dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 🔎] Claude Shanons 1948 Publication that introduced ngrams and information theory: https://people.math.harvard.edu/~ctm/home/text/others/shannon/entropy/entropy.pdf
[2 🔎] Blog that shows how Claude Shanon linked Language to Math: https://www.linkedin.com/pulse/claude-shannons-information-theory-language-models-luis-lastras/
[3 🔎] Section 3.9 talks more about ngram model: https://web.stanford.edu/~jurafsky/slp3/3.pdf
[4 🔎] This paper improves ngram, allowing it to predict words it has never seen before via smoothing: https://www-i6.informatik.rwth-aachen.de/publications/download/951/Kneser-ICASSP-1995.pdf
PLAYLISTS FROM MY CHANNEL
⭕ Transformers from scratch playlist: https://www.youtube.com/watch?v=QCJQG4DuHT0&list=PLTl9hO2Oobd97qfWC40gOSU8C0iu0m2l4
⭕ ChatGPT Playlist of all other videos: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Transformer Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
⭕ Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
⭕ Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD The Origin of Language Models (like ChatGPT)](https://i.ytimg.com/vi/cUsqFx4Sij8/mqdefault.jpg)




![This AI segments ANYTHING ... even VIDEO!
Meet the AI That Segments Anything - SAM 3. Lets talk about this and models that came before it to paint a story.
ABOUT ME
⭕ Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
📚 Medium Blog: https://medium.com/@dataemporium
💻 Github: https://github.com/ajhalthor
👔 LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 📚] pixel class segmentation paper: https://arxiv.org/pdf/1411.4038
[2 📚] MaskFormer paper: https://arxiv.org/pdf/2107.06278
[3 📚] SAM 1 paper: https://arxiv.org/pdf/2304.02643
[4 📚] SAM 2 paper: https://arxiv.org/pdf/2408.00714
[5 📚] SAM 3 paper: https://arxiv.org/pdf/2511.16719
PLAYLISTS FROM MY CHANNEL
⭕ Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
⭕ Transformers from Scratch: https://www.youtube.com/playlist?list=PLTl9hO2Oobd97qfWC40gOSU8C0iu0m2l4
⭕ ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
⭕ Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
⭕ The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
⭕ Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
⭕ Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
📕 Mathematics for Machine Learning: https://imp.i384100.net/MathML
📕 Calculus: https://imp.i384100.net/Calculus
📕 Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
📕 Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
📕 Linear Algebra: https://imp.i384100.net/LinearAlgebra
📕 Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
📕 ⭐ Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
📕 Python for Everybody: https://imp.i384100.net/python
📕 MLOps Course: https://imp.i384100.net/MLOps
📕 Natural Language Processing (NLP): https://imp.i384100.net/NLP
📕 Machine Learning in Production: https://imp.i384100.net/MLProduction
📕 Data Science Specialization: https://imp.i384100.net/DataScience
📕 Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 Introduction
00:20 How AI segmented before
01:47 Introducing the model that segments anything (SAM)
03:30 We can extend to video (SAM 2)
05:35 Detect multiple objects with SAM 3
09:10 A Concise Summary This AI segments ANYTHING ... even VIDEO!](https://i.ytimg.com/vi/eYBbw5SXvUM/mqdefault.jpg)