Spaces:
Running
Running
Sébastien De Greef
commited on
Commit
•
41d4352
1
Parent(s):
e70db4f
feat: Update online learning resources, YouTube videos, and channels in index.qmd
Browse files- src/index.qmd +11 -4
- src/theory/activations.qmd +2 -0
- src/theory/architectures.qmd +2 -0
src/index.qmd
CHANGED
@@ -6,11 +6,10 @@ This repository is my personal collection of recipes and notebooks, documenting
|
|
6 |
|
7 |
::: {.callout-tip}
|
8 |
## Use the search box
|
9 |
-
|
10 |
If you are looking for something in particular use the searchbox to find the correct page
|
11 |
:::
|
12 |
|
13 |
-
Most of my learning was done with online resources, here is a list of channels and video I've found the most usefull and channels or persons you should follow :
|
14 |
|
15 |
### YouTube Channels
|
16 |
|
@@ -40,16 +39,24 @@ Most of my learning was done with online resources, here is a list of channels a
|
|
40 |
|
41 |
- [Harvard CS50’s Artificial Intelligence with Python – Full University Course](https://www.youtube.com/watch?v=5NgNicANyqM)
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
- [Deep Learning Course for Beginners](https://www.youtube.com/watch?v=HJd1I3FdSnY)
|
44 |
|
45 |
- [Keras Deep Learning Building Blocks](https://www.youtube.com/watch?v=_DpsRVHVeR4&list=PLgJhDSE2ZLxbuDYAn_AF-wHVOYIhqujT-)
|
46 |
|
|
|
|
|
47 |
- [Reinforcement Learning with Python by Nicholas Renotte](https://www.youtube.com/playlist?list=PLgNJO2hghbmjlE6cuKMws2ejC54BTAaWV)
|
48 |
|
49 |
- [MLOps Explained](https://www.youtube.com/watch?v=ZVWg18AXXuE)
|
50 |
|
51 |
-
- [Build a Virtual World Filled with Self-Driving Cars – JavaScript Tutorial](https://www.youtube.com/watch?v=5iHejdqYIa8)
|
52 |
-
|
53 |
### Other Videos
|
54 |
|
55 |
- [Mo Gawdat : Ex-Google Officer Finally Speaks Out On The Dangers Of AI!](https://www.youtube.com/watch?v=bk-nQ7HF6k4)
|
|
|
6 |
|
7 |
::: {.callout-tip}
|
8 |
## Use the search box
|
|
|
9 |
If you are looking for something in particular use the searchbox to find the correct page
|
10 |
:::
|
11 |
|
12 |
+
Most of my learning was done with online resources, here is a list of channels and video I've found the most usefull and channels or persons you should follow : (these are just the tip of the iceberg of all valuable knowledge you can find on youtube to become an AI expert)
|
13 |
|
14 |
### YouTube Channels
|
15 |
|
|
|
39 |
|
40 |
- [Harvard CS50’s Artificial Intelligence with Python – Full University Course](https://www.youtube.com/watch?v=5NgNicANyqM)
|
41 |
|
42 |
+
- [Build a Virtual World Filled with Self-Driving Cars – JavaScript Tutorial](https://www.youtube.com/watch?v=5iHejdqYIa8)
|
43 |
+
|
44 |
+
- [Andrew NG: Machine Learning Projects Complete Course](https://youtu.be/Ux1Di2mAsGs?si=y-zyWEH-zUpP9JJx)
|
45 |
+
|
46 |
+
- [The Most Important Algorithm in Machine Learning](https://www.youtube.com/watch?v=SmZmBKc7Lrs)
|
47 |
+
|
48 |
+
- [Intro to Data Science from Steve Brunton](https://www.youtube.com/playlist?list=PLMrJAkhIeNNQV7wi9r7Kut8liLFMWQOXn)
|
49 |
+
|
50 |
- [Deep Learning Course for Beginners](https://www.youtube.com/watch?v=HJd1I3FdSnY)
|
51 |
|
52 |
- [Keras Deep Learning Building Blocks](https://www.youtube.com/watch?v=_DpsRVHVeR4&list=PLgJhDSE2ZLxbuDYAn_AF-wHVOYIhqujT-)
|
53 |
|
54 |
+
- [But what is a neural network?, Learning, Backpropagation etc](https://www.youtube.com/watch?v=aircAruvnKk&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi)
|
55 |
+
|
56 |
- [Reinforcement Learning with Python by Nicholas Renotte](https://www.youtube.com/playlist?list=PLgNJO2hghbmjlE6cuKMws2ejC54BTAaWV)
|
57 |
|
58 |
- [MLOps Explained](https://www.youtube.com/watch?v=ZVWg18AXXuE)
|
59 |
|
|
|
|
|
60 |
### Other Videos
|
61 |
|
62 |
- [Mo Gawdat : Ex-Google Officer Finally Speaks Out On The Dangers Of AI!](https://www.youtube.com/watch?v=bk-nQ7HF6k4)
|
src/theory/activations.qmd
CHANGED
@@ -18,6 +18,8 @@ When choosing an activation function, consider the following:
|
|
18 |
|
19 |
- **Experimentation:** Try different activations and evaluate their performance on your specific task.
|
20 |
|
|
|
|
|
21 |
[Slideshow](activations_slideshow.qmd)
|
22 |
|
23 |
{{< embed ActivationFunctions.ipynb#fig-overview >}}
|
|
|
18 |
|
19 |
- **Experimentation:** Try different activations and evaluate their performance on your specific task.
|
20 |
|
21 |
+
[But what is a neural network?](https://youtu.be/aircAruvnKk?si=64sscTHzYeZ9x-5L)
|
22 |
+
|
23 |
[Slideshow](activations_slideshow.qmd)
|
24 |
|
25 |
{{< embed ActivationFunctions.ipynb#fig-overview >}}
|
src/theory/architectures.qmd
CHANGED
@@ -6,6 +6,8 @@ Neural network architectures are foundational frameworks designed to tackle dive
|
|
6 |
|
7 |
The architecture of a neural network dictates how information flows and is processed. It determines the arrangement and connectivity of layers, the type of data processing that occurs, and how input data is ultimately transformed into outputs. The choice of a suitable architecture is crucial because it impacts the efficiency, accuracy, and feasibility of training models on given datasets.
|
8 |
|
|
|
|
|
9 |
## Feedforward Neural Networks (FNNs)
|
10 |
|
11 |
A basic neural network architecture where data flows only in one direction, from input layer to output layer, without any feedback loops. Feedforward Neural Networks are the simplest type of neural network architecture where connections between the nodes do not form a cycle. This is ideal for problems where the output is directly mapped from the input.
|
|
|
6 |
|
7 |
The architecture of a neural network dictates how information flows and is processed. It determines the arrangement and connectivity of layers, the type of data processing that occurs, and how input data is ultimately transformed into outputs. The choice of a suitable architecture is crucial because it impacts the efficiency, accuracy, and feasibility of training models on given datasets.
|
8 |
|
9 |
+
[Neural Network Architectures & Deep Learning](https://www.youtube.com/watch?v=oJNHXPs0XDk)
|
10 |
+
|
11 |
## Feedforward Neural Networks (FNNs)
|
12 |
|
13 |
A basic neural network architecture where data flows only in one direction, from input layer to output layer, without any feedback loops. Feedforward Neural Networks are the simplest type of neural network architecture where connections between the nodes do not form a cycle. This is ideal for problems where the output is directly mapped from the input.
|