MLPClassifier(hidden_layer_sizes=(350,), 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=(350,), max_iter=50, random_state=1)
Model: \"sequential_7\"\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│ 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│ 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":158},{"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":"from keras.utils import plot_model\n\n# Plot the model architecture and save the image to 'mlp-mnist_plot.png'\nplot_model(model, to_file='mlp-mnist_plot.png', \n show_shapes=True, \n show_layer_names=True, \n dpi=50)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T19:49:41.089184Z","iopub.execute_input":"2024-12-05T19:49:41.08984Z","iopub.status.idle":"2024-12-05T19:49:41.271559Z","shell.execute_reply.started":"2024-12-05T19:49:41.089807Z","shell.execute_reply":"2024-12-05T19:49:41.27055Z"}},"outputs":[{"execution_count":159,"output_type":"execute_result","data":{"image/png":"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","text/plain":"
| \n | accuracy | \nloss | \nval_accuracy | \nval_loss | \n
|---|---|---|---|---|
| 0 | \n0.935148 | \n0.215215 | \n0.967333 | \n0.104622 | \n
| 1 | \n0.972704 | \n0.088361 | \n0.973667 | \n0.089396 | \n
| 2 | \n0.982093 | \n0.056605 | \n0.976333 | \n0.090389 | \n
| 3 | \n0.986982 | \n0.040483 | \n0.976167 | \n0.093837 | \n
| 4 | \n0.989000 | \n0.034770 | \n0.980833 | \n0.078220 | \n