IBM offers Watson Natural Language Understanding, an NLP application supplying interpretation of unstructured textual data and language concept models.
N/A
TensorFlow
Score 8.1 out of 10
N/A
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
I prefer Pytorch overall, recent models are often only available with pytorch PyTorch is also easier to use and it is often easier to find support for PyTorch code nowadays than TensorFlow Also it seems like lots of Google internal resource uses Jax. I mostly uses TensorFlow to …
Can't seem to choose any deep learning platform in the above, so I'll list it here: 1. Apache MXNet: this has been used for one of our main algorithms for search as an end-to-end pipeline. We chose this because of the Scala bindings, which makes it easier to integrate with out …
TensorFlow provides a wide range of algorithms with more detail and customization options compared to others. Also, the library is advanced and updates regularly for optimization and new functions.
Most of the machine learning platforms these days support integration with R and Python libraries. So, the use of reusable libraries is not an issue. TensorFlow performs well in cloud hosting and support for GPU/TPU. However, where it lacks compared to Azure is a graphical …
Thought about alternatives like scikit-learn, xgboost, pytorch, caffe2, fastai exist, but they don't offer as many tools and functionality as TensorFlow does. It is better to inanest in a eco-system which is very active and well maintained by giants. Being open source, one can …
Keras is built on top of TensorFlow, but it is much simpler to use and more Python style friendly, so if you don't want to focus on too many details or control and not focus on some advanced features, Keras is one of the best options, but as far as if you want to dig into more, …
Theano is a Python library and is good for making algorithms from scratch. It is an alternative to Tensor flow. We used tensor flow because it is open source Java source and easy to learn and use.
TensorFlow is developed and maintained by Google. It's the engine behind a lot of …
There are lots of competitors with this library, but I think TensorFlow is the best thing for deep learning. Although it has a sharp learning curve, it's worth learning. It easy to deploy its model on Android. Keras is very good option too it, easy. In Keras, writing the neural …
I have used keras and matlab along with this. Also used Caffe and pyTorch sometimes, but all of them are not as powerful as TensorFlow. Keras is in good competition with TensorFlow but Keras won't allow you a lot of customization in your algorithms. And TensorFlow gives you the …
One major advantage of TensorFlow over Keras and other deep learning libraries is that it is the most powerful. It gives you power to write your own full customised algorithm that is not available in Keras. And it is fast too as compared to another tool as it can perform better …
I have used Theano to develop machine learning models, like writing the neural network. TensorFlow has reinforcement learning support and lot more algorithms while Theano does come with lots of prebuilt tools. TensorFlow provides data visualisation tools and it is possible to …
IBM Watson Natural Language Understanding is a Swiss Army knife that can be used in many scenarios. An extensive list of easy to use APIs is provided making it very easy to integrate it in any environment. The text analysis is decent and above market average. It generates results in many forms to suit may scenarios (important keywords, concepts, sentiment analysis, etc.).
Whenever the problem has the demand for a neural networks based solution, Tensorflow (TF) is a great fit.
The tf.dataset API makes it really simple to create complex data pipelines in a few lines of code.
tf.estimators API abstracts all the complex computation graph creation logic making it very simple to get started.
Eager execution makes it simple to develop a TF graph as debugging the code would be like any other imperative Python program.
TF abstracts all the complexities of scaling it to multiple machines. It has various code and data distribution algorithms ready to use.
Projects like TensorBoard make monitoring the training process really easy. It also gives the ability to view embeddings without any extra code. Their What-If is extremely useful for poking and understanding a black box model. It also has tools to visualize data to quickly check for anomalies.
TF Autograph aims to covert any normal Python code into a distributed program which is quite handy to scale an existing code base.
Data pipeline implementation is quite good, loading large amounts of data and pre-process it in an efficient way is no more issue for us
It supports all major DL algorithms and network layouts such as ConvNets, RNN, LSTMs, Word2Vec, and even the latest transformer architecture
The abstraction for the device is perfectly done and its support seamlessly for multiple GPU and even TPU will bring a lot of performance gain for enterprise scoped solution while still keep the flexibility
The TensorBoard is amazing. I haven't seen a similar thing in other frameworks on the market. It allows us to quickly understand and debug the model with the info visualization which makes understanding much better
A very supportive community, which is the key for sharing the ideas and find the quick and best solutions
It would be much better if they could provide good documentation and easy ways to understand concepts.
It is difficult to understand the concept behind for example, Tensor Graph, which takes a lot of time.
As you have to write everything, it is time consuming to write the implementation of whole neural network. It would be better if they can provide some wrapper library to make things easier.
Community support for TensorFlow is great. There's a huge community that truly loves the platform and there are many examples of development in TensorFlow. Often, when a new good technique is published, there will be a TensorFlow implementation not long after. This makes it quick to ally the latest techniques from academia straight to production-grade systems. Tooling around TensorFlow is also good. TensorBoard has been such a useful tool, I can't imagine how hard it would be to debug a deep neural network gone wrong without TensorBoard.
Can't seem to choose any deep learning platform in the above, so I'll list it here: 1. Apache MXNet: this has been used for one of our main algorithms for search as an end-to-end pipeline. We chose this because of the Scala bindings, which makes it easier to integrate with out JVM backend. MXNet seems comparable to TensorFlow, although community support is not as good as TensorFlow, and there are issues with memory leaks that are being worked on. TensorFlow in general is easier to use, but MXNet isn't too far behind. 2. Keras: still a favorite. Often I use this when paired with TensorFlow. TensorFlow 2.0 will make it even easier. 3. PyTorch: only used it a little, so it's hard to provide a good opinion. 4. DL4J: used it initially in an early days project because it has good JVM support. Harder to used not because of poor API design, but because community support is lacking and features don't come out as fast as TensorFlow.
Positive Impact- As I mentioned before its open source. Very easy to learn for average programmer/ developer. We were able to design a POC model for understanding the patient appointment cancellation snd reasons behind it in 3 week time frame.
Negative Impact- If you are using tensor flow for small project it works fine. If you are trying to build a model for face recognition it will be hard to program and train the system. It needs data to be processed before hand cannot learn on the go.
