eVision

  My Computer Won't Wake Up From the Sleep Mode If your computer isn't turning on properly, it may be stuck in Sleep Mode. Sleep Mode is a power-saving function designed to conserve energy and save wear and tear on your computer system. The monitor and other functions automatically shut down after a set period of inactivity. Once the computer is needed again, it starts back up and recalls all the previously open programs, allowing it to start processing again much faster than a full start-up. Sometimes a computer can get stuck in Sleep Mode and troubleshooting is required. Step 1 Plug your computer into a wall socket if it isn't already. If your batteries are running low, the computer may not have enough power to come out of Sleep Mode. VIDEO OF THE DAY Volume 0% 00:21   Step 2 Push any key on the keyboard. Many computers respond to any activity and come out of Sleep Mode with the push of a key. Step 3 Search your keyboard for a sleep-specific key. It is normally near the t...

  Base Model To see how we can prevent overfitting, we first need to create a base model to compare the improved models to. The base model is a simple keras model with two hidden layers with 128 and 64 neurons. You can check it out here: model = keras . Sequential () model . add ( keras . layers . Dense ( 300 , activation = tf . nn . relu , input_dim = 300 )) model . add ( keras . layers . Dense ( 128 , activation = tf . nn . relu )) model . add ( keras . layers . Dense ( 64 , activation = tf . nn . relu )) model . add ( keras . layers . Dense ( 1 , activation = tf . nn . sigmoid )) model . compile ( optimizer = 'adam' , loss = 'binary_crossentropy' , metrics = [ 'accuracy' ]) history = model . fit ( df_train , train_labels , batch_size = 32 , epochs = 100 , validation_split = 0.2 , shuffle = True ) With this model we can achieve a training accuracy of over 97%, but a validation accuracy of only about 60%. In the graphic below we can se...