- 13
- 3 661
Nogunumo
Japan
Приєднався 4 жов 2022
Building a new intelligence.
AI Devlog #7: Working on CNN, and some improvements.
In this video, I share an update on my recent work. I think 3-dimensional data in CNNs is quite cumbersome to handle.
▶︎ About Nogunumo ◀︎
Welcome to the channel! I'm exploring AI and machine learning technologies, sharing insights, updates, and behind-the-scenes looks at my development process. If you’re into AI, machine learning, or tech innovation, this is the place for you.
0:00 Intro
0:15 Removed class-based models
1:46 No more Preprocessing files
2:37 Move all models from lyrs files to example folder
3:23 Made a new file called strings
3:53 Updated error-handling approach
7:05 Leveraging GPU for basic arithmetic operations
11:45 Began development of CNN
#machinelearning #deeplearning #forwardpropagation #backpropagation
▶︎ About Nogunumo ◀︎
Welcome to the channel! I'm exploring AI and machine learning technologies, sharing insights, updates, and behind-the-scenes looks at my development process. If you’re into AI, machine learning, or tech innovation, this is the place for you.
0:00 Intro
0:15 Removed class-based models
1:46 No more Preprocessing files
2:37 Move all models from lyrs files to example folder
3:23 Made a new file called strings
3:53 Updated error-handling approach
7:05 Leveraging GPU for basic arithmetic operations
11:45 Began development of CNN
#machinelearning #deeplearning #forwardpropagation #backpropagation
Переглядів: 223
Відео
Recurrent Neural Network: Gated Recurrent Unit (GRU) Built from Scratch in C++!
Переглядів 105Місяць тому
This time, I learned so much about sequential models, especially while explaining the concepts in detail! It's definitely faster than LSTMs. Enjoy the video! 0:00 Intro 1:13 Vanishing and exploding gradients 2:58 Preprocessing 3:23 Initialize the parameters in the constructor 4:46 forward() function 8:15 BPTT 9:06 Demo 11:02 Outro #machinelearning #deeplearning #forwardpropagation #backpropagation
Long Short-Term Memory (LSTM): Built from Scratch in C++!
Переглядів 188Місяць тому
I thought it would take more time to implement, but it didn't. I guess that's because it's essentially one of the RNNs, just a more advanced version. One thing to note is that I still had to use the Adam optimizer, which I think was due to the short sequence length I chose. Additionally, I had to slice the weights to focus only on the portions that contributed to the hidden states and to ensure...
Recurrent Neural Network: Built from Scratch in C++!
Переглядів 614Місяць тому
Finally, I implemented it! Everything was challenging-data preparation, forward and backpropagation, and especially the optimizer. It just wouldn't work without Adam! I guess that's why LSTMs were invented. Enjoy the video! 0:00 Intro 0:34 Preprocessing 1:09 Prepare x and y 3:11 Forward propagation 6:59 BPTT 11:11 Demo 19:40 Outro #recurrentneuralnetwork #machinelearning #deeplearning #forwardp...
AI Devlog #6: Fixing Loss Calculation
Переглядів 1002 місяці тому
Before the fix, the loss fluctuated a lot, but when I incorporated batch sizes into the loss calculation, the losses began to decrease more smoothly. While it still fluctuates, this is not due to miscalculations; rather, it's because the model isn't perfectly generalized to the dataset, which I need to improve in the future. Enjoy the video!
Seq2seq: TextVectorization!
Переглядів 1125 місяців тому
Hey everyone! I'm building the AGI. Feel free to drop your questions in the comments, and I'd love to hear your thoughts on the process! 0:00 Intro 1:52 How it works 5:33 Demo 9:06 Outro
AI Devlog #5: Refactoring the Training Code
Переглядів 155Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the regularizations I added to the model. Please share any questions or suggestions below. Hope you enjoy! 0:00 Intro 1:10 Refactorization for forward propagation 3:02 Refactorization for logging metrics 5:48 Refactorization for parameter initializations 7:53 Backpropagation 16:00 Using only one hidden lay...
AI Devlog #4: L1L2 Regularization!
Переглядів 230Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the regularizations I added to the model. Please share any questions or suggestions below. Hope you enjoy! 0:00 Introduction 1:39 Realization of immature 2:48 Benefits of stopped writing code in NumPy 7:45 Explanation of L2Regularizations 18:28 Demonstrate the consequences of introducing regularization 20:...
AI Devlog #3: Gradient Clipping!
Переглядів 242Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the gradient clipping I added to the model. Please share any questions or suggestions below. Hope you enjoy! 0:00 Introduction 1:08 Gradient clipping explanation 2:35 Assessing model's performance 3:24 I need to decrease number of hidden layer 8:43 Removed hyperparameters.h 11:02 Future updates
AI Devlog #2: Adding momentum to the model
Переглядів 161Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the momentum I added to the model. Please share any questions or suggestions below. Hope you enjoy! 0:00 Introduction 0:42 Deleting NumPy code 1:33 C code is slower than NumPy code 3:04 Explanation for Momentum 8:27 Result after adding the momentum 14:34 Code maintenance
AI Devlog #1: New activation and loss functions!
Переглядів 82Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the activation and loss functions I added, and other new updates. Please share any questions or suggestions below. Hope you enjoy! 0:00 Introduction 0:23 Learning rate scheduler 4:39 Changing variable names for partial derivatives 6:06 Softmax activation 9:25 Fix partial derivative calculation 13:10 Catego...
Neural Network: Overview 2
Переглядів 1,3 тис.Рік тому
I am implementing machine learning models in C and CUDA. In today's video, I will explain the conceptual overview of a simple neural network written in C and CUDA from scratch. Please share any questions or suggestions below. Hope you enjoy! 0:00 Introduction 0:23 Load the dataset 1:27 Preprocessing 2:38 Initializing parameters 4:53 Mini-batch gradient descent 5:49 Forward propagation 6:23 Back...
Neural Network: Overview 1
Переглядів 173Рік тому
I am working on a project to develop an artificial general intelligence (AGI) from scratch using C and CUDA. In today's video, I will be showing my first feedforward neural network written in C and CUDA. Although it is not perfect yet, I just wanted to show it to everyone. I will improve it more and upload the videos. Hope you enjoy!
Some points on your video that I at least think you should think about if you make more 1. Lose the glasses if possible, makes you look... not serious. 2. Think about getting a better mic 3. If this video is only to showcase what you have built, i guess thats fine but either you need some more entusiasm in your voice to have such a lenghty video to keep people in it or edit it ( i world prefer you do that either way) in a way where you get to the point faster. If you are unsure how to entertain or be engageing maby shorter clips is easier to handle? 4. Even if this only is a showcase there is alot of code to go through and will quickly get overwelming for someone to get into. This is where some powerpoint could have been nice to have going through the math. 5. If this was ment to be a tutorial, do not show all the code directly. It is the worst way to teach someone how something works. Building it up while explaining what you are doing and why it works. It is good for you to get a deeper knowlage of it all and a learning experience for yourself. Keep working on it, as someone that also built DNN from scratch in C# i know this is complex sometimes. But it is fun and that is why we do it Also I'm Swedish so excuse my English😂
Finally! Someone made a tutorial of creating more than simple MLP in C++!!! You are the GOAT, man! Thank You!
Thanks! Really glad you found it helpful-means a lot!
Cool thumbnail Nogu! So good to see you upload
thx!