From 309634de87a2755feb527bc18ab1c1b31208b3fc Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Thu, 21 Nov 2024 14:55:24 +0000 Subject: [PATCH 1/7] Fixing 2023-24 tutorials pages --- our-initiatives/tutorials/2023-2024/index.mdx | 30 ++++++++++--------- .../tutorials/2023-2024/intro-to-ai.md | 8 +++-- .../tutorials/2023-2024/intro-to-python.md | 6 ++-- 3 files changed, 24 insertions(+), 20 deletions(-) diff --git a/our-initiatives/tutorials/2023-2024/index.mdx b/our-initiatives/tutorials/2023-2024/index.mdx index 53410e5..3ae133c 100644 --- a/our-initiatives/tutorials/2023-2024/index.mdx +++ b/our-initiatives/tutorials/2023-2024/index.mdx @@ -8,7 +8,7 @@ import DocCardList from '@theme/DocCardList' # πŸ’» Machine Learning Tutorial Series -Welcome to season 4 (2024-25) of the beginner machine learning tutorial series of the UCL Artificial Intelligence Society! +Welcome to season 4 (2023-24) of the beginner machine learning tutorial series of the UCL Artificial Intelligence Society! If you have any questions about our content or machine learning more generally, feel free to ask us at the next session or make a forum post on the [UCLAIS Discord server](https://discord.gg/KSUZuQx?ltclid=3f704b3b-9044-415a-a2d7-e41007214187). You can also join our WhatsApp group chat through this [link](https://chat.whatsapp.com/JWEJn7OWvWE8MBfm2uSBhh). @@ -16,10 +16,12 @@ If you have any questions about our content or machine learning more generally, This academic year, the tutorial series is being delivered by the following people: -- [Sergi Kavtaradze](#) (Head of Tutorials) -- [Zachary Baker](#) (ML Officer) -- [Paul Chaminieu](#) (ML Officer) -- [Anna-Maria](#) (ML Officer) +- [Angela Yu](#) (Head of Tutorials) +- [Damien Bose](#) (ML Officer) +- [Suhail Merali](#) (ML Officer) +- [Arham Ali](#) (Tutorials Reviewer) +- [Ilai Bachrach](#) (ML Officer) +- [James Ray](#) (ML Officer) ## DOXA Challenges @@ -42,22 +44,22 @@ During the first half term, we aim to cover basic concepts of **classical ML**: - Tutorial 0: **Introduction to AI** - Tutorial 1: **Introduction to Python** - Tutorial 2: **Regression** -- Tutorial 3: **Classification 1** -- Tutorial 4: **Classification 2** +- Tutorial 3: **Classification** (Doxa 1) After reading week, we will focus on **Deep Learning**! -- Tutorial 4: **Neural Networks** -- Tutorial 5: **Visual Computing I** (Doxa) -- Tutorial 6: **Generative visual computing** -- Tutorial 7: **Recurrent Neural Networks** (Doxa) -- Tutorial 8: **Introduction to Transforments** +- Tutorial 4: **Neural Networks** (Doxa 2) +- Tutorial 5: **Visual Computing I** +- Tutorial 6: **Visual Computing II** +- Tutorial 7: **Recurrent Neural Networks** +- Tutorial 8: **ClimateHack.AI Workshop** ### Term 2 - Tutorial 9: **Natural Language Processing I** - Tutorial 10: **Natural Language Processing II** -- Tutorial 11: **Graph neural networks / Reinforcement learning** +- Tutorial 11: **Reinforcement Learning** +- Tutorial 12: **ML Career Perspectives and Ongoing Learning Strategies** ## Previous Seasons @@ -66,4 +68,4 @@ The content and resources from previous years are available on GitHub: - [Season 1 (2020/21)](https://github.com/UCLAIS/Machine-Learning-Tutorials) – led by [Danny Toeun Kim](https://github.com/kimdanny) - [Season 2 (2021/22)](https://github.com/UCLAIS/ML-Tutorials-Season-2) – led by [Martynas Pocius](https://github.com/MartynasPocius) - [Season 3 (2022/23)](https://github.com/UCLAIS/ml-tutorials-season-3) – led by [Filip TrhlΓ­k](https://trhlikfilip.com/) -- [Season 4 (2023/24)](https://github.com/UCLAIS/ml-tutorials-season-4) – led by [Angela Yu](https://github.com/angela24680403) + diff --git a/our-initiatives/tutorials/2023-2024/intro-to-ai.md b/our-initiatives/tutorials/2023-2024/intro-to-ai.md index ff7c55e..e839c6a 100644 --- a/our-initiatives/tutorials/2023-2024/intro-to-ai.md +++ b/our-initiatives/tutorials/2023-2024/intro-to-ai.md @@ -4,12 +4,14 @@ sidebar_position: 2 # 0: Introduction to AI -**Date: 2nd October 2024** +**Date: 11th October 2023** πŸ’‘ We're excited to present our **Introduction to Artificial Intelligence** tutorial session! In this session, we'll take you on a journey to understand the different perspectives on AI and its evolution. We will also cover definitions of the key components of AI, including **Machine Learning** (ML) and **Deep Learning** (DL). **Generative AI**, especially models like GPT-3 and updated versions of this, has created significant attention in recent years. These models have demonstrated the ability to **generate human-like text and creative content** across multiple areas, ranging from **text to image and audio synthesis**. We will showcase some of these examples in the session! Please note that though this session is introducing what AI is in general, we will be mainly **focusing our series on ML**. πŸ’‘ -You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 0 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-0/ai_code_examples.ipynb) +You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 0 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-4/blob/main/week-0/ai_code_examples.ipynb) You can access our **slides** here: πŸ’» [**Tutorial 0 Slides**](https://www.canva.com/design/DAFm9tHNEDM/cEKEXWzmazR5KKN-7f06tw/edit) -The **recording** from this session is available here: 🎀 [**Tutorial 0 Recording**](https://www.youtube.com/watch?v=OFS90-FX6pg) +The **recording** from this session is available here: 🎀 [**Tutorial 0 Recording**](https://youtu.be/TzEdKvNFztI?si=3TVzoaWvdTi0U57-) + +(Apologies for the sound quality, you may need to turn it to max volume.) diff --git a/our-initiatives/tutorials/2023-2024/intro-to-python.md b/our-initiatives/tutorials/2023-2024/intro-to-python.md index 275347d..3233072 100644 --- a/our-initiatives/tutorials/2023-2024/intro-to-python.md +++ b/our-initiatives/tutorials/2023-2024/intro-to-python.md @@ -4,13 +4,13 @@ sidebar_position: 3 # 1: Introduction to Python -**Date: 9th October 2024** +**Date: 18th October 2023** πŸ’‘ **Python** is a common, **high-level programming language** known for its simplicity - this means that if you are new to coding, this language would be the perfect place to start! It has access to a lot of **libraries and frameworks**, including **NumPy**, **Pandas**, and **TensorFlow**, that are particularly useful for our ML series. In this session, the Tutorials team is collaborating with the Development team to create a workshop where we can provide direct help with **setting up your environment** and **walk you through Python exercises** we have prepared for you to get started! πŸ’‘ -You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 1 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-1/1_1_introduction_to_python.ipynb) +You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 1 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-4/blob/main/week-1/1_1_introduction_to_python.ipynb) -Here are the **exercises** you can go through: πŸ“˜ [**Tutorial 1 Exercises**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-1/1_2_python_exercises.ipynb) +Here are the **exercises** you can go through: πŸ“˜ [**Tutorial 1 Exercises**](https://github.com/UCLAIS/ml-tutorials-season-4/blob/main/week-1/1_2_python_exercises.ipynb) You can access our **slides** here: πŸ’» [**Tutorial 1 Slides**](https://www.canva.com/design/DAFmvE-ptx0/lyY0SiOcjgSxrb201KcC8w/edit) From 701f6228d2ecd8405ced475284ba1b779417738b Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Thu, 21 Nov 2024 14:58:51 +0000 Subject: [PATCH 2/7] Adding week 5 and week 6 content --- our-initiatives/tutorials/2024-2025/index.mdx | 5 +++-- .../tutorials/2024-2025/neural-networks.md | 15 +++++++++++++++ .../tutorials/2024-2025/visual-computing-1.md | 16 ++++++++++++++++ 3 files changed, 34 insertions(+), 2 deletions(-) create mode 100644 our-initiatives/tutorials/2024-2025/neural-networks.md create mode 100644 our-initiatives/tutorials/2024-2025/visual-computing-1.md diff --git a/our-initiatives/tutorials/2024-2025/index.mdx b/our-initiatives/tutorials/2024-2025/index.mdx index 3d69f30..c81fb61 100644 --- a/our-initiatives/tutorials/2024-2025/index.mdx +++ b/our-initiatives/tutorials/2024-2025/index.mdx @@ -18,6 +18,7 @@ This academic year, the tutorial series is being delivered by the following peop - [Zachary Baker](#) (ML Officer) - [Paul Chaminieu](#) (ML Officer) - [Anna-Maria](#) (ML Officer) +- [Franciszek Nowak](#) (ML Officer - Visual Computing I) ## DOXA Challenges @@ -40,7 +41,7 @@ During the first half term, we aim to cover basic concepts of **classical ML**: - Tutorial 0: **Introduction to AI** - Tutorial 1: **Introduction to Python** - Tutorial 2: **Regression** -- Tutorial 3: **Classification I** +- Tutorial 3: **Classification I** (Doxa) - Tutorial 4: **Classification II** After reading week, we will focus on **Deep Learning**! @@ -55,7 +56,7 @@ After reading week, we will focus on **Deep Learning**! - Tutorial 10: **Natural Language Processing I** - Tutorial 11: **Natural Language Processing II** -- Tutorial 12: **Graph neural networks / Reinforcement learning** +- Tutorial 12: **Graph Neural Networks / Reinforcement Learning** ## Previous Seasons diff --git a/our-initiatives/tutorials/2024-2025/neural-networks.md b/our-initiatives/tutorials/2024-2025/neural-networks.md new file mode 100644 index 0000000..368b7ee --- /dev/null +++ b/our-initiatives/tutorials/2024-2025/neural-networks.md @@ -0,0 +1,15 @@ +--- +sidebar_position: 7 +--- + +# 4: Neural Networks + +**Date: 13th November 2024** + +πŸš€ Exciting news! This week, we're embarking on a thrilling journey into the world of Deep Learning with our first tutorial on Neural Networks (NN)! 🧠 We'll kick things off by exploring the basic building blocks of these powerful models: the neurons. πŸŽ‡ Get ready to unravel the mysteries of activation functions that determine how each neuron responds and the crucial role of loss in guiding our model's learning process. πŸ“ˆ As we venture further, you'll discover how the forward pass calculates the outputs of our model, and how backwards propagation works to refine the parameters iteratively. 🎨 The real beauty of NN lies in their ability to process unstructured data like images, learning to recognize intricate patterns for tasks such as image recognition - but we'll save that excitement for next time! πŸš€ + +You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 5 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-5/neural_networks.ipynb) + +You can access our **slides** here: πŸ’» [**Tutorial 5 Slides**](https://www.canva.com/design/DAGSELwCr3o/Tazd7gsGR7ldtOsRMiWuEQ/view?utm_content=DAGSELwCr3o&utm_campaign=designshare&utm_medium=link&utm_source=editor) + +The **recording** from this session is available here: 🎀 [**Tutorial 5 Recording**](https://youtu.be/j9w3-LQ4wHU) diff --git a/our-initiatives/tutorials/2024-2025/visual-computing-1.md b/our-initiatives/tutorials/2024-2025/visual-computing-1.md new file mode 100644 index 0000000..9ebab5a --- /dev/null +++ b/our-initiatives/tutorials/2024-2025/visual-computing-1.md @@ -0,0 +1,16 @@ +--- +sidebar_position: 8 +--- + +# 5: Visual Computing I + +**Date: 20th November 2024** + +🌟 Get ready to dive into the captivating realm of visual computing! πŸ“· This amazing field encompasses a wide array of techniques designed to process and analyze visual data, such as images and videos. πŸŽ₯ We'll explore the art of image representation, where we transform visual content into digital formats, typically using pixels with RGB values. πŸ–ŒοΈ We'll also delve into the world of preprocessing techniques like normalization, resizing, and rotation, which help us create the perfect dataset for training our neural networks. 🧩 Get ready to be amazed by the power of Convolutional Neural Networks (CNNs) 🎨! These networks use kernels to extract features and uncover the hidden patterns within visual data. πŸ” We'll learn about classic CNN architectures like AlexNet, VGG, and ResNet, and see how they've revolutionized image classification and object detection. 🌍 Buckle up for an unforgettable adventure in the realm of visual computing! πŸš€ + +Make sure to participate in the [**DOXA Challenge**](https://doxaai.com/competition/cifar-10) for this week on the CIFAR-10 dataset. The default solution is already provided, but we recomend you change the architecture and add augmentations. Also have a look at our **demonstration notebook** here: πŸ“˜ [**Tutorial 6 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-6/Visual_Computing_1.ipynb) + +You can access our **slides** here: πŸ’» [**Tutorial 6 Slides**](https://www.canva.com/design/DAGSEOBHg_w/FBDwdQyMvbNmJZtvT8Vp5Q/view?utm_content=DAGSEOBHg_w&utm_campaign=designshare&utm_medium=link&utm_source=editor) + +The **recording** from this session is available here (This week it is on Zoom): 🎀 [**Tutorial 6 Recording**](https://ucl.zoom.us/rec/play/7z4igfPHxlWIGoGQAUNYEYa6q1EU97cxe_DRL5cTw5oszHd5vnS5uDnZav_u8cAft6fKduXlzQs_yg8p.rsDAE1RghIGcH4iz?canPlayFromShare=true&from=share_recording_detail&continueMode=true&componentName=rec-play&originRequestUrl=https%3A%2F%2Fucl.zoom.us%2Frec%2Fshare%2Fm4kFm2Uy9xid-_FOAPS2vBYewgqRS3z0mrN27nHgaWPZouAbpiSoKfi6RRyjFe9w.MuHWjQK2b_e5qfoE) +**Passcode**: =SoFE*7V From 259986a15c158e7d0713c3406d43c360f7b0919c Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Wed, 27 Nov 2024 22:03:38 +0000 Subject: [PATCH 3/7] adding visual computing II --- .../tutorials/2024-2025/visual-computing-2.md | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 our-initiatives/tutorials/2024-2025/visual-computing-2.md diff --git a/our-initiatives/tutorials/2024-2025/visual-computing-2.md b/our-initiatives/tutorials/2024-2025/visual-computing-2.md new file mode 100644 index 0000000..4043bae --- /dev/null +++ b/our-initiatives/tutorials/2024-2025/visual-computing-2.md @@ -0,0 +1,27 @@ +--- +sidebar_position: 9 +--- + +# 6: Visual Computing II + +**Date: 27th November 2024** + +πŸ’‘ This week, we'll dive into the exciting world of generative models for computer vision! We'll explore how to create models that can learn the intrinsic features of a dataset and generate new images. We'll focus on building an **auto-encoder**, a powerful tool for capturing the essence of visual data in a compressed **latent space**. + +A latent space is a lower-dimensional representation that encodes the most important features of the data. By learning this compact representation, generative models can create new images that resemble the original dataset. We'll introduce you to various state-of-the-art models used in industry and research, such as **Variational Auto-Encoders** (VAEs), **Generative Adversarial Networks** (GANs) and **Diffussion Models**!πŸ’‘ + +Also, I want to remind you guys that we are running a [**DOXA challenge**](https://doxaai.com/competition/cifar-10) and which you can get prizes for! + +‒⁠ ⁠⁠1st place will get a Mystery prize 🍫 + AI Society Shirt πŸ‘•+ PenπŸ–ŠοΈ +‒⁠ ⁠⁠2nd place will receive AI Society Shirt πŸ‘• + Pen. πŸ–ŠοΈ(**NOTE** that 1st and 2nd place have to achieve a score greater than 0.8074) +‒⁠ ⁠⁠⁠The remaining participants will receive UCL AI Society Pens as long as you can get a score above Jeremy (0.6077) + +The deadline for submission is Wednesday, December 4th, 5:59PM which is right before our next session on RNNs. + +For more information on how to do better in the challenge access the last 10 slides and watch our tutorial recording below. + +You can access our **slides** here: πŸ’» [**Tutorial 7 Slides**](https://www.canva.com/design/DAGSEDAKiHs/jRkDsMJRc65jzSe0KgmbYg/view?utm_content=DAGSEDAKiHs&utm_campaign=designshare&utm_medium=link&utm_source=editor) + +The **recording** from this session is available here: 🎀 [**Tutorial 7 Recording**](https://youtu.be/5ceoctSndC0) + +We did not go through the **demonstration notebook** during session, but you can access our it here: πŸ“˜ [**Tutorial 7 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-7/VAE_andAE.ipynb) \ No newline at end of file From 1e798ae9ed84cf2ee39e84e1bda37936d6a6b691 Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Wed, 27 Nov 2024 22:09:21 +0000 Subject: [PATCH 4/7] Updating week 7 --- our-initiatives/tutorials/2024-2025/visual-computing-2.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/our-initiatives/tutorials/2024-2025/visual-computing-2.md b/our-initiatives/tutorials/2024-2025/visual-computing-2.md index 4043bae..d6ed665 100644 --- a/our-initiatives/tutorials/2024-2025/visual-computing-2.md +++ b/our-initiatives/tutorials/2024-2025/visual-computing-2.md @@ -2,7 +2,7 @@ sidebar_position: 9 --- -# 6: Visual Computing II +# 7: Generative Visual Computing **Date: 27th November 2024** From 5ef705a077b2b743a7534e62f4d71038df39df9f Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Mon, 2 Dec 2024 12:37:27 +0000 Subject: [PATCH 5/7] Adding James to index.mdx files --- our-initiatives/tutorials/2024-2025/index.mdx | 1 + our-initiatives/tutorials/index.mdx | 10 ++++++---- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/our-initiatives/tutorials/2024-2025/index.mdx b/our-initiatives/tutorials/2024-2025/index.mdx index c81fb61..f750c4a 100644 --- a/our-initiatives/tutorials/2024-2025/index.mdx +++ b/our-initiatives/tutorials/2024-2025/index.mdx @@ -19,6 +19,7 @@ This academic year, the tutorial series is being delivered by the following peop - [Paul Chaminieu](#) (ML Officer) - [Anna-Maria](#) (ML Officer) - [Franciszek Nowak](#) (ML Officer - Visual Computing I) +- [James Ray](#) (ML Officer - Generative Visual Computing) ## DOXA Challenges diff --git a/our-initiatives/tutorials/index.mdx b/our-initiatives/tutorials/index.mdx index fca712d..9aa2bb4 100644 --- a/our-initiatives/tutorials/index.mdx +++ b/our-initiatives/tutorials/index.mdx @@ -1,5 +1,5 @@ --- -sidebar_position: 0 +sidebar_position: 1 --- import DocCardList from '@theme/DocCardList' @@ -18,6 +18,8 @@ This academic year, the tutorial series is being delivered by the following peop - [Zachary Baker](#) (ML Officer) - [Paul Chaminieu](#) (ML Officer) - [Anna-Maria](#) (ML Officer) +- [Franciszek Nowak](#) (ML Officer - Visual Computing I) +- [James Ray](#) (ML Officer - Generative Visual Computing) ## DOXA Challenges @@ -40,7 +42,7 @@ During the first half term, we aim to cover basic concepts of **classical ML**: - Tutorial 0: **Introduction to AI** - Tutorial 1: **Introduction to Python** - Tutorial 2: **Regression** -- Tutorial 3: **Classification I** +- Tutorial 3: **Classification I** (Doxa) - Tutorial 4: **Classification II** After reading week, we will focus on **Deep Learning**! @@ -48,14 +50,14 @@ After reading week, we will focus on **Deep Learning**! - Tutorial 5: **Neural Networks** - Tutorial 6: **Visual Computing I** (Doxa) - Tutorial 7: **Generative visual computing** -- Tutorial 8: **Recurrent Neural Networks** (Doxa) +- Tutorial 8: **Recurrent Neural Networks** - Tutorial 9: **Introduction to Transforments** ### Term 2 - Tutorial 10: **Natural Language Processing I** - Tutorial 11: **Natural Language Processing II** -- Tutorial 12: **Graph neural networks / Reinforcement learning** +- Tutorial 12: **Graph Neural Networks / Reinforcement Learning** ## Previous Seasons From 0f06187f1a8c1e2f35c60b65b657785bd15144f7 Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Mon, 2 Dec 2024 16:00:11 +0000 Subject: [PATCH 6/7] Fixing indexing of the titles --- our-initiatives/tutorials/2024-2025/neural-networks.md | 2 +- our-initiatives/tutorials/2024-2025/visual-computing-1.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/our-initiatives/tutorials/2024-2025/neural-networks.md b/our-initiatives/tutorials/2024-2025/neural-networks.md index 368b7ee..78e80f7 100644 --- a/our-initiatives/tutorials/2024-2025/neural-networks.md +++ b/our-initiatives/tutorials/2024-2025/neural-networks.md @@ -2,7 +2,7 @@ sidebar_position: 7 --- -# 4: Neural Networks +# 5: Neural Networks **Date: 13th November 2024** diff --git a/our-initiatives/tutorials/2024-2025/visual-computing-1.md b/our-initiatives/tutorials/2024-2025/visual-computing-1.md index 9ebab5a..96ef40a 100644 --- a/our-initiatives/tutorials/2024-2025/visual-computing-1.md +++ b/our-initiatives/tutorials/2024-2025/visual-computing-1.md @@ -2,7 +2,7 @@ sidebar_position: 8 --- -# 5: Visual Computing I +# 6: Visual Computing I **Date: 20th November 2024** From 55f4606ab04bf13ad14a8270fbe5ac21d834872f Mon Sep 17 00:00:00 2001 From: Sergikavtaradze <20skavtaradze@gmail.com> Date: Mon, 16 Dec 2024 07:36:14 +0300 Subject: [PATCH 7/7] fixing indexing + adding week 8,9 --- .../tutorials/2024-2025/_category_.json | 2 +- .../tutorials/2024-2025/intro_to_transformers.md | 14 ++++++++++++++ our-initiatives/tutorials/2024-2025/rnns.md | 14 ++++++++++++++ our-initiatives/tutorials/_category_.json | 2 +- 4 files changed, 30 insertions(+), 2 deletions(-) create mode 100644 our-initiatives/tutorials/2024-2025/intro_to_transformers.md create mode 100644 our-initiatives/tutorials/2024-2025/rnns.md diff --git a/our-initiatives/tutorials/2024-2025/_category_.json b/our-initiatives/tutorials/2024-2025/_category_.json index 49fc1f2..3438085 100644 --- a/our-initiatives/tutorials/2024-2025/_category_.json +++ b/our-initiatives/tutorials/2024-2025/_category_.json @@ -1,6 +1,6 @@ { "label": "2024-2025", - "position": 1, + "position": 2, "link": { "type": "doc", "id": "tutorials/2024-2025/index" diff --git a/our-initiatives/tutorials/2024-2025/intro_to_transformers.md b/our-initiatives/tutorials/2024-2025/intro_to_transformers.md new file mode 100644 index 0000000..93a787a --- /dev/null +++ b/our-initiatives/tutorials/2024-2025/intro_to_transformers.md @@ -0,0 +1,14 @@ +--- +sidebar_position: 11 +--- + +# 9: Introduction to Transformers + +**Date: 11th December 2024** + +πŸ’‘ **Transformers** were initially introduced for the purpose of **machine translation**, but is now the most prevalent (State Of The Art) architecture used for virtually all deep learning tasks. Unlike traditional neural networks, Transformers rely on a mechanism called **attention**, which allows them to focus on relevant parts of the input sequence. Unlike RNNs this architecture takes in sequential input data in parallel. + +Central to this model are the **encoder-decoder blocks**, where input data undergoes **tokenization** and is embedded into vectors with **positional encodings** to capture word order. This week, we will explore the **attention mechanism**, including **multi-headed attention**, the structure of **encoder and decoder blocks**, and the processes involved in **training Transformers**, such as **tokenization, masking strategies**, and managing **computational costs**. +πŸ’‘ + +You can access our **slides** here: πŸ’» [**Tutorial 9 Slides**](https://www.canva.com/design/DAGYOwRh8u8/xn2OqkUHgTGClSoYOhSxYQ/view?utm_content=DAGYOwRh8u8&utm_campaign=designshare&utm_medium=link2&utm_source=uniquelinks&utlId=ha097b37913) diff --git a/our-initiatives/tutorials/2024-2025/rnns.md b/our-initiatives/tutorials/2024-2025/rnns.md new file mode 100644 index 0000000..62ce21f --- /dev/null +++ b/our-initiatives/tutorials/2024-2025/rnns.md @@ -0,0 +1,14 @@ +--- +sidebar_position: 10 +--- + +# 8: Recurrent Neural Networks + +**Date: 4th December 2024** + +πŸ’‘ **Recurrent Neural Networks (RNNs)** are a class of models designed to handle sequential data, such as **time series** or **language**, by using **feedback loops** to maintain **context** over time. This week, we will explore the fundamentals of RNNs, the challenges of training themβ€”especially backpropagation through timeβ€”and the introduction of variants like **Long Short-Term Memory (LSTM)** networks that better capture **long-term dependencies**. We will briefly mention contrast these approaches with **transformers**, which have largely replaced RNNs and LSTMs in state-of-the-art applications by using self-attention mechanisms to model sequence elements in parallel, ultimately offering a broader perspective on modern sequence modeling techniques.πŸ’‘ + +You can access our **demonstration notebook** here: πŸ“˜ [**Tutorial 8 Notebook**](https://github.com/UCLAIS/ml-tutorials-season-5/blob/main/week-8/rnn.ipynb) + +You can access our **slides** here: πŸ’» [**Tutorial 8 Slides**](https://www.canva.com/design/DAGSEPaNv_I/RpD2FqJCqnRyZxwa_cvsGQ/view?utm_content=DAGSEPaNv_I&utm_campaign=designshare&utm_medium=link2&utm_source=uniquelinks&utlId=h053c9bd49f) + diff --git a/our-initiatives/tutorials/_category_.json b/our-initiatives/tutorials/_category_.json index 95200eb..29375bb 100644 --- a/our-initiatives/tutorials/_category_.json +++ b/our-initiatives/tutorials/_category_.json @@ -1,6 +1,6 @@ { "label": "πŸ’» ML Tutorial Series", - "position": 2, + "position": 1, "link": { "type": "doc", "id": "tutorials/2024-2025/index"