1
$\begingroup$

I'm attempting to use a sequence of numbers (of fixed length) in order to predict a binary output (either 1 or 0) using Keras and a recurrent neural network.

Each training example/sequence has 10 timesteps, each containing a vector of 5 numbers, and each training output consists of either a 1 or 0. The ratio of 1s to 0s is around 1:3. There are approximately 100,000 training examples.

I have tried implementing this using Keras, but the loss stops decreasing after the first epoch of training. I've also attempted modifying the hyper-parameters, but to no avail. Is there something I'm missing here?

The training inputs are as follows: (zero padded)

array([[[0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        ...,
        [1.24829336, 0.96461449, 3.35142857, 0.74675   , 0.776075  ],
        [1.248303  , 0.96427925, 0.        , 1.317225  , 1.317225  ],
        [1.24831488, 0.96409169, 2.74857143, 1.353775  , 1.377825  ]],

       [[0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        ...,
        [1.24969672, 0.96336315, 0.        , 1.319725  , 1.319725  ],
        [1.24968077, 0.96331624, 0.        , 1.33535   , 1.33535   ],
        [1.24969598, 0.96330252, 5.01714286, 1.3508    , 1.3947    ]],

       [[0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        ...,
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        [1.25715364, 0.95520672, 2.57714286, 1.04565   , 1.0682    ],
        [1.25291274, 0.96879701, 7.76      , 1.311875  , 1.379775  ]],

       ...,

       [[0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        [0.        , 0.        , 0.        , 0.        , 0.        ],
        ...,
        [1.24791079, 0.96561021, 4.44      , 0.7199    , 0.75875   ],
        [1.25265263, 0.96117379, 2.09714286, 0.7636    , 0.78195   ],
        [1.25868651, 0.96001674, 3.01142857, 1.35235   , 1.3787   ]]])

The training outputs are as follows:

array([[0.],
       [0.],
       [0.],
       ...,
       [1.],
       [0.],
       [0.]])

This is the model I have attempted to train:

#Model 
model = Sequential()
model.add(LSTM(100, input_shape= (10, 5)))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, validation_data = (X_test, y_test), epochs = 100, batch_size = 1000)
$\endgroup$
9
  • $\begingroup$ How many training instances do you have? $\endgroup$
    – JahKnows
    Apr 6 '19 at 17:25
  • $\begingroup$ I have around 100,000 instances $\endgroup$
    – George Lee
    Apr 6 '19 at 17:52
  • 1
    $\begingroup$ Welcome to SE.DataScience! Please provide these two: (1) ratio of 1s to all instances, and (2) value of loss for first, second, and third epochs. I may have an answer. $\endgroup$
    – Esmailian
    Apr 6 '19 at 17:56
  • 1
    $\begingroup$ Can you give us a snippet of the data please? $\endgroup$
    – JahKnows
    Apr 6 '19 at 17:59
  • $\begingroup$ (1) 1:4 (2) Loss actually flattens out after around 3-4 epochs, at around 0.5870, 0.5805, 0.5804 $\endgroup$
    – George Lee
    Apr 6 '19 at 18:26

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.