MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=50, random_state=1)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=50, random_state=1)
MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=50, random_state=1)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=50, random_state=1)
Model: \"sequential_1\"\n\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ dense_3 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m200,960\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m65,792\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_5 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m2,570\u001b[0m │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n","text/html":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ dense_3 (Dense) │ (None, 256) │ 200,960 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_4 (Dense) │ (None, 256) │ 65,792 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_1 (Dropout) │ (None, 256) │ 0 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_5 (Dense) │ (None, 10) │ 2,570 │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m269,322\u001b[0m (1.03 MB)\n","text/html":"
Total params: 269,322 (1.03 MB)\n\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m269,322\u001b[0m (1.03 MB)\n","text/html":"
Trainable params: 269,322 (1.03 MB)\n\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":"
Non-trainable params: 0 (0.00 B)\n\n"},"metadata":{}}],"execution_count":37},{"cell_type":"markdown","source":"- The above listing shows the model summary of the proposed network. It requires a total of 269,322 parameters.\n\n- This is substantial considering that we have a simple task of classifying MNIST digits. So, MLPs are not parameter efficient. \n\n- The total number of parameters required can be computed as follows:\n\n - From input to Dense layer: 784 × 256 + 256 = 200,960. \n \n - From first Dense to second Dense: 256 × 256 + 256 = 65,792. \n \n - From second Dense to the output layer: 10 × 256 + 10 = 2,570. \n \n - The total is 200,690 + 65,972 + 2,570 = 269,322.","metadata":{}},{"cell_type":"markdown","source":"- Another way of verifying the network is by calling the **plot_model()** method as follows:","metadata":{}},{"cell_type":"code","source":"\n\nplot_model(model, to_file='mlp-mnist_plot.png', \n show_shapes=True, \n show_layer_names=True, \n dpi=50, \n show_layer_activations=True,\n show_trainable=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T10:36:43.371235Z","iopub.execute_input":"2024-11-27T10:36:43.371589Z","iopub.status.idle":"2024-11-27T10:36:43.64714Z","shell.execute_reply.started":"2024-11-27T10:36:43.371559Z","shell.execute_reply":"2024-11-27T10:36:43.645977Z"}},"outputs":[{"execution_count":38,"output_type":"execute_result","data":{"image/png":"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","text/plain":"
| \n | accuracy | \nloss | \nval_accuracy | \nval_loss | \n
|---|---|---|---|---|
| 0 | \n0.361667 | \n1.655607 | \n0.660167 | \n0.963758 | \n
| 1 | \n0.735833 | \n0.809439 | \n0.855167 | \n0.517329 | \n
| 2 | \n0.849259 | \n0.505239 | \n0.899833 | \n0.350764 | \n
| 3 | \n0.895074 | \n0.363671 | \n0.929167 | \n0.265078 | \n
| 4 | \n0.918463 | \n0.285933 | \n0.940833 | \n0.218778 | \n