Main body of the essay (Neural networks in the automotive sector)

Neural networks are being used in numerous commercial products in numerous industries. In the automotive industry neural networks have many potential applications both inside the vehicle, such as self-driving, advanced driving assistance systems (ADAS), and outside the vehicle such as during the development stage (Luckow et al.,2016).

There are mainly three types of neural networks which are mainly used in the automotive industry, recurrent neural networks, reinforcement learning NNs and convolutional NNs (Hernandez, 2017). A recurrent neural network (RNN) is a type of artificial neural network which uses sequential data or time series data (IBM,2021). In autonomous vehicles they are used to track moving objects and detect possible collisions, and with time RNNs can predict paths of moving objects, for example a moving pedestrian coming close to a road will probably mean that the pedestrian will cross it and the RNNs will make a decision on what the vehicle should do to avoid any danger, the other type of NNs are CNNs (Convolutional Neural Networks) which are used for visual pattern recognition and are used for obstacle detection in automotive world (Cadence PCB solutions, 2021). The best feature of CNNs and RNNs is their ability to increase accuracy over time using data, a self-driving car company Wayve believes that the two are the solution for self-driving cars to be truly successful, they claim that no matter how many programs a vehicle has, it will never be able to predict every situation, they argue that it is best to implement AI into vehicles to predict even in new situations that have not been programmed (ibid).

Here are a few use cases for neural networks in automotive industry, first is smart manufacturing  in which neural networks can help increase operational efficiency, additionally there is 'connected vehicles' which contains personal assistants and infotainment systems, furthermore and most importantly is the autonomous driving (NetApp, 2021).However, there are a few challenges for NNs in the automotive sector, while NNs empower vehicles to learn, it still lacks ethical reasoning that humans use, an example is a car choosing to hit multiple pedestrians or driving off a cliff and kill its occupants, such situations must be programmed by engineers and programmers, which make it very difficult to reach fully self-driving vehicles and creates pressure and hesitation which may continue for years (Cadence, 2021).