This review paper explores the applications of machine learning (ML) and deep learning (DL) in challenging various agricultural problems. Agriculture includes both growing of crops and rearing of livestock. The agriculture sector is the source of production of a vast variety of food and largely contributes to a country’s economy. Agriculture plays a key role in the lucrative prosperity of any country which not only fulfils human’s basic needs, addressing the dare of feeding nearly 10 billion people by 2050, but also a source of employment. Deep learning (DL) is a strong data-analysis and image-processing technique that has revealed appreciable promise in the agricultural sector. Machine learning (ML), a middlemost subset of artificial intelligence. Machine learning harnesses computational algorithms directly from raw data and it is being used in almost every field of agriculture. Cattle farming refer to the breeding of animals to obtain products such as milk, meat and other dairy products for human consumption. A lot of deep learning models have been applied to solve diverse problems related to cattle health and welfare, classification of cattle for yield production and identification. In this paper the recent advancements in the use of ML and DL techniques such as Convolutional neural networks (CNN) , Generative Adversarial Networks (GANs), Recurrent Neural networks (RNN), Alexnet etc., are explored in various sectors of Agriculture. CNN models are used in identification of plant disease, pest, weed, nematode etc., and soil nutrient diagnosis; Deep learning is widely used in smart agriculture and precision livestock farming and integrates a variety of digital technologies.