Skip to content

Commit b81cf94

Browse files
avaaminiavaamini
committed
fixing names to point to new repo address
1 parent d932d4a commit b81cf94

24 files changed

+88
-88
lines changed

‎lab1/PT_Part1_Intro.ipynb

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@
1010
" <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
1111
" <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
1212
" Visit MIT Deep Learning</a></td>\n",
13-
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab1/PT_Part1_Intro.ipynb\">\n",
13+
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/MITDeepLearning/introtodeeplearning/blob/master/lab1/PT_Part1_Intro.ipynb\">\n",
1414
" <img src=\"https://i.ibb.co/2P3SLwK/colab.png\" style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
15-
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab1/PT_Part1_Intro.ipynb\">\n",
15+
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/MITDeepLearning/introtodeeplearning/blob/master/lab1/PT_Part1_Intro.ipynb\">\n",
1616
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
1717
"</table>\n",
1818
"\n",
@@ -203,7 +203,7 @@
203203
"\n",
204204
"A convenient way to think about and visualize computations in a machine learning framework like PyTorch is in terms of graphs. We can define this graph in terms of tensors, which hold data, and the mathematical operations that act on these tensors in some order. Let's look at a simple example, and define this computation using PyTorch:\n",
205205
"\n",
206-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/add-graph.png)"
206+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/add-graph.png)"
207207
]
208208
},
209209
{
@@ -235,7 +235,7 @@
235235
"\n",
236236
"Now let's consider a slightly more complicated example:\n",
237237
"\n",
238-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
238+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
239239
"\n",
240240
"Here, we take two inputs, `a, b`, and compute an output `e`. Each node in the graph represents an operation that takes some input, does some computation, and passes its output to another node.\n",
241241
"\n",
@@ -306,7 +306,7 @@
306306
"\n",
307307
"Let's consider the example of a simple perceptron defined by just one dense (aka fully-connected or linear) layer: $ y = \\sigma(Wx + b) $, where $W$ represents a matrix of weights, $b$ is a bias, $x$ is the input, $\\sigma$ is the sigmoid activation function, and $y$ is the output.\n",
308308
"\n",
309-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
309+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
310310
"\n",
311311
"We will use `torch.nn.Module` to define layers -- the building blocks of neural networks. Layers implement common neural networks operations. In PyTorch, when we implement a layer, we subclass `nn.Module` and define the parameters of the layer as attributes of our new class. We also define and override a function [``forward``](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.forward), which will define the forward pass computation that is performed at every step. All classes subclassing `nn.Module` should override the `forward` function.\n",
312312
"\n",

‎lab1/PT_Part2_Music_Generation.ipynb

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@
1010
" <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
1111
" <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
1212
" Visit MIT Deep Learning</a></td>\n",
13-
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab1/PT_Part2_Music_Generation.ipynb\">\n",
13+
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/MITDeepLearning/introtodeeplearning/blob/master/lab1/PT_Part2_Music_Generation.ipynb\">\n",
1414
" <img src=\"https://i.ibb.co/2P3SLwK/colab.png\" style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
15-
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab1/PT_Part2_Music_Generation.ipynb\">\n",
15+
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/MITDeepLearning/introtodeeplearning/blob/master/lab1/PT_Part2_Music_Generation.ipynb\">\n",
1616
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
1717
"</table>\n",
1818
"\n",
@@ -399,7 +399,7 @@
399399
"* [`nn.LSTM`](https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html): Our LSTM network, with size `hidden_size`.\n",
400400
"* [`nn.Linear`](https://pytorch.org/docs/stable/generated/torch.nn.Linear.html): The output layer, with `vocab_size` outputs.\n",
401401
"\n",
402-
"<img src=\"https://raw.githubusercontent.com/aamini/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/>\n",
402+
"<img src=\"https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/>\n",
403403
"\n",
404404
"\n",
405405
"\n",
@@ -415,7 +415,7 @@
415415
"* [`tf.keras.layers.Dense`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense): The output layer, with `vocab_size` outputs.\n",
416416
"\n",
417417
"\n",
418-
"<img src=\"https://raw.githubusercontent.com/aamini/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/> -->"
418+
"<img src=\"https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/> -->"
419419
]
420420
},
421421
{
@@ -875,7 +875,7 @@
875875
"\n",
876876
"* At each time step, the updated RNN state is fed back into the model, so that it now has more context in making the next prediction. After predicting the next character, the updated RNN states are again fed back into the model, which is how it learns sequence dependencies in the data, as it gets more information from the previous predictions.\n",
877877
"\n",
878-
"![LSTM inference](https://raw.githubusercontent.com/aamini/introtodeeplearning/2019/lab1/img/lstm_inference.png)\n",
878+
"![LSTM inference](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2019/lab1/img/lstm_inference.png)\n",
879879
"\n",
880880
"Complete and experiment with this code block (as well as some of the aspects of network definition and training!), and see how the model performs. How do songs generated after training with a small number of epochs compare to those generated after a longer duration of training?"
881881
]

‎lab1/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# MIT 6.S191 Lab 1: Intro to Deep Learning in Python and Music Generation with RNNs
22

3-
![alt text](https://github.com/aamini/introtodeeplearning/raw/master/lab1/img/music_waveform.png)
3+
![alt text](https://github.com/MITDeepLearning/introtodeeplearning/raw/master/lab1/img/music_waveform.png)
44
## Part 1: Intro to Deep Learning in Python -- TensorFlow and PyTorch
55
TensorFlow ("TF") and PyTorch ("PT") are software libraries used in machine learning. Here we'll learn how computations are represented and how to define simple neural networks in TensorFlow and PyTorch. The TensorFlow labs will be prefixed by `TF`; PyTorch labs will be prefixed by `PT`.
66

‎lab1/TF_Part1_Intro.ipynb

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@
1010
" <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
1111
" <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
1212
" Visit MIT Deep Learning</a></td>\n",
13-
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab1/TF_Part1_Intro.ipynb\">\n",
13+
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/MITDeepLearning/introtodeeplearning/blob/master/lab1/TF_Part1_Intro.ipynb\">\n",
1414
" <img src=\"https://i.ibb.co/2P3SLwK/colab.png\" style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
15-
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab1/TF_Part1_Intro.ipynb\">\n",
15+
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/MITDeepLearning/introtodeeplearning/blob/master/lab1/TF_Part1_Intro.ipynb\">\n",
1616
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
1717
"</table>\n",
1818
"\n",
@@ -208,7 +208,7 @@
208208
"\n",
209209
"A convenient way to think about and visualize computations in TensorFlow is in terms of graphs. We can define this graph in terms of Tensors, which hold data, and the mathematical operations that act on these Tensors in some order. Let's look at a simple example, and define this computation using TensorFlow:\n",
210210
"\n",
211-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/add-graph.png)"
211+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/add-graph.png)"
212212
]
213213
},
214214
{
@@ -240,7 +240,7 @@
240240
"\n",
241241
"Now let's consider a slightly more complicated example:\n",
242242
"\n",
243-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
243+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
244244
"\n",
245245
"Here, we take two inputs, `a, b`, and compute an output `e`. Each node in the graph represents an operation that takes some input, does some computation, and passes its output to another node.\n",
246246
"\n",
@@ -311,7 +311,7 @@
311311
"\n",
312312
"Let's first consider the example of a simple perceptron defined by just one dense layer: $ y = \\sigma(Wx + b)$, where $W$ represents a matrix of weights, $b$ is a bias, $x$ is the input, $\\sigma$ is the sigmoid activation function, and $y$ is the output. We can also visualize this operation using a graph:\n",
313313
"\n",
314-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
314+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
315315
"\n",
316316
"Tensors can flow through abstract types called [```Layers```](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Layer) -- the building blocks of neural networks. ```Layers``` implement common neural networks operations, and are used to update weights, compute losses, and define inter-layer connectivity. We will first define a ```Layer``` to implement the simple perceptron defined above."
317317
]

‎lab1/TF_Part2_Music_Generation.ipynb

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@
1010
" <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
1111
" <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
1212
" Visit MIT Deep Learning</a></td>\n",
13-
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab1/TF_Part2_Music_Generation.ipynb\">\n",
13+
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/MITDeepLearning/introtodeeplearning/blob/master/lab1/TF_Part2_Music_Generation.ipynb\">\n",
1414
" <img src=\"https://i.ibb.co/2P3SLwK/colab.png\" style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
15-
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab1/TF_Part2_Music_Generation.ipynb\">\n",
15+
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/MITDeepLearning/introtodeeplearning/blob/master/lab1/TF_Part2_Music_Generation.ipynb\">\n",
1616
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
1717
"</table>\n",
1818
"\n",
@@ -399,7 +399,7 @@
399399
"* [`tf.keras.layers.Dense`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense): The output layer, with `vocab_size` outputs.\n",
400400
"\n",
401401
"\n",
402-
"<img src=\"https://raw.githubusercontent.com/aamini/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/>"
402+
"<img src=\"https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2019/lab1/img/lstm_unrolled-01-01.png\" alt=\"Drawing\"/>"
403403
]
404404
},
405405
{
@@ -858,7 +858,7 @@
858858
"\n",
859859
"* At each time step, the updated RNN state is fed back into the model, so that it now has more context in making the next prediction. After predicting the next character, the updated RNN states are again fed back into the model, which is how it learns sequence dependencies in the data, as it gets more information from the previous predictions.\n",
860860
"\n",
861-
"![LSTM inference](https://raw.githubusercontent.com/aamini/introtodeeplearning/2019/lab1/img/lstm_inference.png)\n",
861+
"![LSTM inference](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2019/lab1/img/lstm_inference.png)\n",
862862
"\n",
863863
"Complete and experiment with this code block (as well as some of the aspects of network definition and training!), and see how the model performs. How do songs generated after training with a small number of epochs compare to those generated after a longer duration of training?"
864864
]

‎lab1/solutions/PT_Part1_Intro_Solution.ipynb

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@
1010
" <td align=\"center\"><a target=\"_blank\" href=\"http://introtodeeplearning.com\">\n",
1111
" <img src=\"https://i.ibb.co/Jr88sn2/mit.png\" style=\"padding-bottom:5px;\" />\n",
1212
" Visit MIT Deep Learning</a></td>\n",
13-
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/aamini/introtodeeplearning/blob/master/lab1/solutions/PT_Part1_Intro_Solution.ipynb\">\n",
13+
" <td align=\"center\"><a target=\"_blank\" href=\"https://colab.research.google.com/github/MITDeepLearning/introtodeeplearning/blob/master/lab1/solutions/PT_Part1_Intro_Solution.ipynb\">\n",
1414
" <img src=\"https://i.ibb.co/2P3SLwK/colab.png\" style=\"padding-bottom:5px;\" />Run in Google Colab</a></td>\n",
15-
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/aamini/introtodeeplearning/blob/master/lab1/solutions/PT_Part1_Intro_Solution.ipynb\">\n",
15+
" <td align=\"center\"><a target=\"_blank\" href=\"https://github.com/MITDeepLearning/introtodeeplearning/blob/master/lab1/solutions/PT_Part1_Intro_Solution.ipynb\">\n",
1616
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
1717
"</table>\n",
1818
"\n",
@@ -241,7 +241,7 @@
241241
"\n",
242242
"A convenient way to think about and visualize computations in a machine learning framework like PyTorch is in terms of graphs. We can define this graph in terms of tensors, which hold data, and the mathematical operations that act on these tensors in some order. Let's look at a simple example, and define this computation using PyTorch:\n",
243243
"\n",
244-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/add-graph.png)"
244+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/add-graph.png)"
245245
]
246246
},
247247
{
@@ -282,7 +282,7 @@
282282
"\n",
283283
"Now let's consider a slightly more complicated example:\n",
284284
"\n",
285-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
285+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph.png)\n",
286286
"\n",
287287
"Here, we take two inputs, `a, b`, and compute an output `e`. Each node in the graph represents an operation that takes some input, does some computation, and passes its output to another node.\n",
288288
"\n",
@@ -364,7 +364,7 @@
364364
"\n",
365365
"Let's consider the example of a simple perceptron defined by just one dense (aka fully-connected or linear) layer: $ y = \\sigma(Wx + b) $, where $W$ represents a matrix of weights, $b$ is a bias, $x$ is the input, $\\sigma$ is the sigmoid activation function, and $y$ is the output.\n",
366366
"\n",
367-
"![alt text](https://raw.githubusercontent.com/aamini/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
367+
"![alt text](https://raw.githubusercontent.com/MITDeepLearning/introtodeeplearning/2025/lab1/img/computation-graph-2.png)\n",
368368
"\n",
369369
"We will use `torch.nn.Module` to define layers -- the building blocks of neural networks. Layers implement common neural networks operations. In PyTorch, when we implement a layer, we subclass `nn.Module` and define the parameters of the layer as attributes of our new class. We also define and override a function [``forward``](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.forward), which will define the forward pass computation that is performed at every step. All classes subclassing `nn.Module` should override the `forward` function.\n",
370370
"\n",

0 commit comments

Comments
 (0)