Deep learning techniques are being widely applied to Human Activity Recognition (HAR). This paper describes the implementation and evaluation of a HAR system for daily life activities using the accelerometer of an Iphone-6. This system is based on a deep neural network including convolutional layers for feature extraction from accelerations and fully-connected layers for classification between activities. Different transformations have been applied to the acceleration signals in order to find the appropriate input data to the deep neural network. This study has used acceleration recordings from the MotionSense dataset, where 24 subjects performed 6 activities: walking downstairs, walking upstairs, sitting, standing, walking and jogging. The evaluation has been performed using a subject-wise cross validation: recordings from the same subject do not appear in training and testing sets at the same time. The proposed system has obtained a 9% improvement in accuracy compared to the baseline system based on Support Vector Machines. The best results was obtained using raw data as input to a deep neural network composed of 2 convolutional and 2 max-pooling layers with decreasing kernel sizes. Results suggest that using the module of the Fourier transform as inputs provides better results when classifying only between dynamic activities.